Create natural AI voices instantly in any language - perfect for video creators, developers, and businesses.
Create natural AI voices instantly in any language - perfect for video creators, developers, and businesses. On Nagent, ElevenLabs is exposed as a fully-configurable artificial intelligence integration that any agent can call — 155 actions, and API key authentication. No code is required to wire ElevenLabs into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use ElevenLabs to automate the kinds of tasks artificial intelligence teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire ElevenLabs into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against ElevenLabs, with input parameters and output schema. Drop these into any step of an agent built in Helix.
ELEVENLABS_ADD_A_PRONUNCIATION_DICTIONARYAdds a new pronunciation dictionary from a lexicon file to improve speech synthesis accuracy.
Input parameters
A lexicon file (typically .pls XML) containing pronunciation rules.
A descriptive name for the pronunciation dictionary.
Optional detailed description of the pronunciation dictionary and its purpose.
Access level for the pronunciation dictionary within the workspace (admin, editor, or viewer).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_ADD_OUTBOUND_PHONE_NUMBERTool to import/register a Twilio phone number or SIP trunk into ElevenLabs Agents Platform. Use when you need to provision a phone number for outbound calls and ELEVENLABS_GET_AGENT_DETAILS returns empty phone_numbers. This does NOT purchase a new number; it imports an existing provider configuration into your ElevenLabs workspace.
Input parameters
Twilio Account SID (required when provider is 'twilio')
Descriptive label for the phone number
Twilio Auth Token (required when provider is 'twilio')
Provider type: 'twilio' or 'sip_trunk'
Phone number to import in E.164 format
Region configuration for Twilio phone number.
Enable inbound call capability for this number
Enable outbound call capability for this number
Inbound configuration for SIP trunk.
Outbound configuration for SIP trunk.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_ADD_PROJECTUse to create a new ElevenLabs project for text-to-speech synthesis (e.g., audiobooks); a project `name` is required by the API for creation, and content can be initialized using `from_url` or `from_document`.
Input parameters
A unique name for the project, crucial for its identification and management.
Optional title for the project, distinct from `name` (e.g., for a book title).
Optional author for the project (e.g., for a book).
URL to extract content for initializing the project. Use instead of `from_document`.
Optional ISBN for the project, typically for audiobooks.
Optional URL for a POST request with project conversion status updates.
Document file (e.g..txt.epub.pdf) to upload for initializing project content. Use instead of `from_url`.
Output quality of generated audio.
Model ID for synthesis (e.g., 'eleven_multilingual_v2'; see GET /v1/models); uses default model if unspecified.
Apply general volume normalization to audio output.
Voice ID for titles (see GET /v1/voices); uses ElevenLabs default if unspecified.
Apply ACX (Audiobook Creation Exchange) volume normalization to audio output.
Voice ID for paragraphs (see GET /v1/voices); uses ElevenLabs default if unspecified.
List of pronunciation dictionary locators (format: 'dictionary_id@version_id') for custom pronunciations.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_ADD_PRONUNCIATION_DICTIONARY_FROM_RULESTool to create a new pronunciation dictionary from provided rules for ElevenLabs text-to-speech. Use when you need to define custom pronunciations for specific words or phrases to improve speech accuracy. Supports both alias rules (simple text replacements) and phoneme rules (IPA phonetic notation).
Input parameters
The name of the pronunciation dictionary, used for identification only
List of pronunciation rules defining text replacements. Each rule can be either an alias rule (simple text replacement) or a phoneme rule (phonetic pronunciation using IPA or other alphabet). Minimum 1 rule required.
A description of the pronunciation dictionary, used for identification only
Valid workspace access levels for pronunciation dictionaries.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_ADD_RULES_TO_THE_PRONUNCIATION_DICTIONARYAdds one or more custom pronunciation rules (alias or phoneme) to an existing pronunciation dictionary.
Input parameters
List of pronunciation rule objects, each defining an 'alias' or 'phoneme' transformation for a specific string. - **Alias Rule**: Use `type: "alias"`, `string_to_replace`, and `alias` (replacement text). Example: `{"type": "alias", "string_to_replace": "ASAP", "alias": "as soon as possible"}`. - **Phoneme Rule**: Use `type: "phoneme"`, `string_to_replace`, `phoneme` (phonetic transcription), and `alphabet` (e.g., 'ipa'). Example: `{"type": "phoneme", "string_to_replace": "gnocchi", "phoneme": "ˈɲɔkki", "alphabet": "ipa"}`.
Identifier of an existing pronunciation dictionary to which rules will be added.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_ADD_SHARING_VOICEAdds an existing, shareable voice to a specified user's ElevenLabs account library under a new custom name, requiring the user's public ID and the voice ID.
Input parameters
Name to assign the shared voice in the user's library, displayed on the ElevenLabs website.
Unique identifier of the shared voice to be added.
Public user ID of the ElevenLabs user to whom the shared voice will be added.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_ADD_VOICEAdds a custom voice by uploading audio samples for voice cloning. Requires a name and at least one audio file. Recommended: 1-2 minutes of clear audio without background noise. Supported formats: mp3, wav, ogg. Returns a voice_id that can be used for text-to-speech after processing completes.
Input parameters
Name for the new voice, used as its identifier in the platform.
List of audio files for voice cloning. Each file should be a Supported formats: mp3, wav, ogg. At least one file is required, and 1-2 minutes of clear audio without background noise is recommended.
Optional stringified JSON object of key-value pairs for categorizing the voice. Example: {"accent": "American", "style": "narration"}
Optional description for the voice, detailing its characteristics or intended use cases.
If set to true, will remove background noise from voice samples using the audio isolation model. Only use if samples contain background noise; using it on clean audio can reduce quality.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_ATTACH_PHONE_NUMBER_TO_AGENTTool to assign or unassign an existing imported phone number to an agent by updating the phone number's assigned agent. Use when you need to programmatically route inbound calls to a specific agent or change agent assignment for a phone number.
Input parameters
Descriptive label for the phone number
ID of the agent to assign to the phone number. Set to null to unassign the phone number from any agent.
Type of LiveKit stack to use
The unique identifier of the phone number to update
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CALCULATE_CONVAI_AGENT_LLM_USAGETool to calculate expected number of LLM tokens needed for a conversational AI agent. Use when estimating costs for an agent based on knowledge base size, prompt length, and RAG configuration.
Input parameters
Unique identifier for the agent
Whether RAG is enabled
Length of the prompt in characters
Pages of content in pdf documents OR urls in agent's Knowledge Base
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CALCULATE_CONVAI_LLM_USAGETool to calculate expected LLM usage costs for conversational AI agents. Use when you need to estimate pricing for different LLM models based on prompt length, knowledge base size, and RAG configuration.
Input parameters
Whether RAG (Retrieval-Augmented Generation) is enabled.
Length of the prompt in characters.
Pages of content in PDF documents or URLs in the agent's knowledge base.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CANCEL_CONVAI_BATCH_CALLTool to cancel a running batch call and set all recipients to cancelled status. Use when you need to stop an ongoing batch calling campaign.
Input parameters
Unique identifier of the batch call to cancel
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CONVERT_CHAPTERConverts the textual content of a chapter, identified by `chapter_id` within a `project_id`, into audio format.
Input parameters
Identifier of the chapter to be converted.
Identifier of the project containing the chapter to be converted.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CONVERT_PROJECTConverts an existing ElevenLabs Studio project, including all its chapters and using its configured settings and voices, into speech.
Input parameters
Identifier of the project to convert; find available IDs via the GET /v1/studio/projects endpoint.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CREATE_A_PREVIOUSLY_GENERATED_VOICEFinalizes the creation of a voice using its `generated_voice_id` from a previous generation step by assigning a name, description, and optional labels.
Input parameters
Key-value metadata to associate with the voice.
Name for the newly created voice.
Detailed description for the newly created voice, its characteristics, or intended use.
Identifier of a previously generated voice (e.g., from POST /v1/voice-generation/generate-voice), used to finalize its creation.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CREATE_CONVAI_AGENT_TESTINGTool to create a new ElevenLabs Conversational AI agent response test. Use when you need to set up automated testing for agent responses, tool calls, or conversation simulations. Supports three test types: 'llm' for response validation, 'tool_call' for tool execution verification, and 'simulation' for full conversation testing.
Input parameters
Name for the test case to identify it later
Type of test to create: 'llm' for response testing, 'tool' for tool execution testing, or 'simulation' for conversation simulation testing
Array of messages representing the conversation history to test against. Each message must include role ('user' or 'agent'), time_in_call_secs (float), and optional message text content.
Examples of failed or incorrect agent responses for LLM tests
Examples of successful agent responses for LLM tests
Key-value pairs of variables to be dynamically injected into the test context
Required for 'llm' and 'simulation' types. Natural language description of what constitutes a successful agent response
Required for 'simulation' type. Natural language description of the scenario to simulate in the conversation
For 'simulation' type tests: Maximum number of conversation turns to simulate
For 'tool_call' type tests: Expected parameters for the tool that should be called by the agent
For 'tool_call' type tests: Whether to check if any tool matches the expected call pattern
Metadata from a previous conversation to use as context for this test
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CREATE_CONVAI_KNOWLEDGE_BASETool to add documentation to ElevenLabs Conversational AI knowledge base by uploading a file or referencing a webpage URL. Use when you need to provide reference materials or documentation that agents can access during conversations. Exactly one of 'file' or 'url' must be specified.
Input parameters
URL to a documentation webpage that the agent will have access to. Either 'file' or 'url' must be provided, but not both.
Documentation file to upload. Supported formats: PDF, TXT, DOC, DOCX. Either 'file' or 'url' must be provided, but not both.
Custom, human-readable name for the document in the knowledge base
Specific agent ID to associate this knowledge base document with
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CREATE_CONVAI_KNOWLEDGE_BASE_FILETool to create a knowledge base document from an uploaded file for ElevenLabs Conversational AI agents. Use when you need to provide documentation or reference material that agents can access during conversations. The uploaded file content will be indexed and made available to agents for answering user queries.
Input parameters
Documentation file that the agent will have access to for interacting with users.
A custom, human-readable name for the document. If not provided, the filename will be used.
If set, the created document will be placed inside the given folder. Leave empty to place in root.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CREATE_CONVAI_KNOWLEDGE_BASE_FOLDERTool to create a folder in the ElevenLabs ConvAI knowledge base for organizing documents. Use when you need to group related documents together in a hierarchical structure.
Input parameters
A custom, human-readable name for the folder
If set, the created folder will be placed inside the given parent folder. Leave empty to create at root level.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CREATE_CONVAI_KNOWLEDGE_BASE_RAG_INDEXTool to compute or retrieve RAG indexes for multiple knowledge base documents in batch. Use when you need to enable semantic search on multiple knowledge base documents for conversational AI agents. This endpoint creates embeddings if missing or returns existing indexes, supporting up to 100 documents per request.
Input parameters
List of requested RAG indexes to create or retrieve (1-100 items)
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CREATE_CONVAI_KNOWLEDGE_BASE_TEXTTool to create a knowledge base document with text content in ElevenLabs Conversational AI. Use when you need to add text-based information to the knowledge base for agent reference.
Input parameters
A custom, human-readable name for the document.
Text content to be added to the knowledge base.
If set, the created document will be placed inside the given folder.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CREATE_CONVAI_KNOWLEDGE_BASE_URLTool to create a knowledge base document by scraping the given webpage. Use when you need to add a web page as a knowledge source for a conversational AI agent.
Input parameters
URL to a page of documentation that the agent will have access to in order to interact with users
A custom, human-readable name for the document
If set, the created document or folder will be placed inside the given folder
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CREATE_CONVAI_SECRETTool to create a new secret for the ElevenLabs ConvAI workspace. Use when you need to securely store API keys, tokens, or other sensitive values that your conversational AI agents can reference.
Input parameters
Name identifier for the secret. Must be unique within the workspace.
Type of secret to create. Currently only 'new' is supported by the API.
The secret value to store securely in the workspace.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CREATE_CONVAI_TOOLTool to create a new conversational AI tool in ElevenLabs workspace. Use when adding custom tools for agents to execute during conversations. Supports webhook (external HTTP APIs), client (client-side execution), system (built-in), and MCP (Model Context Protocol) tool types.
Input parameters
Tool name. Must match pattern ^\[a-zA-Z0-9_-\]{1,64}$ (alphanumeric, hyphens, underscores only, no spaces, 1-64 characters)
System tool parameters (required for system tools)
Type of tool to create: 'webhook' for HTTP endpoints, 'client' for client-side execution, 'system' for built-in tools, or 'mcp' for MCP integration
API schema configuration (required for webhook tools). Should include endpoint URL and HTTP method details
Tool parameters schema (for client and MCP tools)
Tool assignments for routing to specific conversations
Tool description explaining what it does
MCP server ID (required for MCP tools)
MCP tool name (required for MCP tools)
Execution mode for the tool.
MCP approval policy.
MCP server name (required for MCP tools)
Sound to play during tool call
Whether the client tool expects a response (for client tools)
Integration type for MCP tools.
MCP input schema (for MCP tools)
Dynamic variables configuration (for webhook and client tools)
MCP tool description (required for MCP tools)
Whether to disable interruptions during tool execution
Force speech before tool execution
Response timeout in seconds
Sound behavior during tool calls.
How to handle tool execution errors.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CREATE_CONVERSATIONAL_AGENTTool to create a new ElevenLabs Conversational AI agent with specified configuration. Use when you need to programmatically set up an agent with custom prompts, voice settings, and behavior. After creating the agent, you can chain other tools to attach phone numbers or configure additional settings.
Input parameters
Human-readable name for the agent
List of tags to organize and categorize the agent
Workflow configuration defining conditional logic, tool execution modes, and conversation flow patterns for the agent
Platform-specific settings including evaluation criteria, widget configuration, data collection schemas, auth requirements, call limits, and privacy settings. For widget.variant, valid values are: 'tiny', 'compact', 'full', or 'expandable'.
Configuration object defining the agent's conversational behavior. Must include agent settings (prompt, llm, language, first_message), and can optionally include asr, tts, turn, conversation, and vad settings. Example: {'agent': {'prompt': {'prompt': 'You are a helpful assistant', 'llm': 'gpt-4o'}}}
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CREATE_MUSIC_PLANTool to generate a music composition plan from a text prompt using ElevenLabs Music API. Use when you need to create a structured plan for music generation with defined styles, sections, and durations. The generated plan can be used as input for actual music generation or as a template for variations.
Input parameters
A simple text prompt to compose a plan from. Describe the musical style, mood, instruments, or other characteristics you want in the composition.
The model to use for the generation.
The length of the composition plan to generate in milliseconds. Must be between 3000ms (3 seconds) and 600000ms (10 minutes). If not provided, the model will choose a length based on the prompt.
Optional source composition plan for generating variations.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CREATES_AUDIONATIVE_ENABLED_PROJECTCreates an ElevenLabs AudioNative project, generating an embeddable audio player from a provided content file using text-to-speech, allowing customization of player appearance, audio settings, and conversion options.
Input parameters
Content file (e.g., TXT, HTML) to be converted into audio.
User-defined name for the AudioNative project.
URL for an image in the AudioNative player; a default or no image is used if omitted.
Set to `True` for a compact player; `False` (default) for standard size.
Title of the content, for display in the AudioNative player.
Author of the content, for display in the AudioNative player.
Identifier for the ElevenLabs TTS model. Allowed models for AudioNative: 'eleven_multilingual_v2', 'eleven_turbo_v2_5', 'eleven_turbo_v2', 'eleven_monolingual_v1', 'eleven_multilingual_v1'. A default is used if omitted.
Identifier for the ElevenLabs voice; a default is used if omitted. See '/v1/voices' for available IDs.
Hex color code for player text (must start with '#', e.g., '#FFFFFF' for white, '#000000' for black).
If `True`, automatically converts content to audio after project creation; `False` (default).
Interval in days for automatic audio reconversion; `0` (default) disables it (e.g., `1` daily, `7` weekly).
Hex color code for player background (must start with '#', e.g., '#000000' for black, '#FFFFFF' for white).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CREATE_SIMILAR_VOICESReturns a list of shared voices similar to the provided audio sample. Use when you need to find voice matches based on audio characteristics. If neither similarity_threshold nor top_k is provided, default values will be applied.
Input parameters
Number of most similar voices to return. If similarity_threshold is provided, fewer voices may be returned. Values range from 1 to 100. Default values will be applied if not specified.
Audio file to find similar voices for. Supported formats: mp3, wav, ogg.
Threshold for voice similarity between provided sample and library voices. Values range from 0 to 2. The smaller the value, the more similar voices will be returned. Default values will be applied if not specified.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CREATE_SINGLE_USE_TOKENTool to generate a time-limited single-use token with embedded authentication for frontend clients. Use when you need secure, temporary access tokens for WebSocket connections or real-time services.
Input parameters
Type of single-use token to generate. Options: 'realtime_scribe' for real-time transcription, 'tts_websocket' for text-to-speech WebSocket connections.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_CREATE_WORKSPACE_WEBHOOKTool to create a new webhook for the workspace with specified authentication type. Use when you need to configure a webhook endpoint to receive notifications from ElevenLabs. The webhook_secret returned should be stored securely for verifying webhook authenticity.
Input parameters
Webhook configuration settings including auth_type, name, and webhook_url
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DELETE_CHAPTERIrreversibly deletes a specific, existing chapter from an existing project, typically to remove unwanted or obsolete content.
Input parameters
Identifier of the chapter to be deleted. To find available `chapter_id`s for a project, you can query GET `https://api.elevenlabs.io/v1/studio/projects/{project_id}/chapters`.
Identifier of the project. To find available `project_id`s, you can query GET `https://api.elevenlabs.io/v1/studio/projects`.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DELETE_CONVAI_AGENTTool to permanently delete a Conversational AI agent by its unique identifier. Use when you need to remove an agent configuration from the ElevenLabs workspace.
Input parameters
The unique identifier of the agent to delete. This is returned on agent creation.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DELETE_CONVAI_AGENT_TESTINGTool to delete an agent response test by ID. Use when you need to remove a test result or clean up test data.
Input parameters
The id of a chat response test. This is returned on test creation.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DELETE_CONVAI_BATCH_CALLINGTool to permanently delete a batch call and all associated recipient records. Conversations remain in history. Use when cleaning up completed or cancelled batch calls.
Input parameters
The unique identifier of the batch call to permanently delete. Format: btcal_<alphanumeric>
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DELETE_CONVAI_CONVERSATIONTool to delete a particular Conversational AI conversation by ID. Use when you need to remove a conversation from the system for cleanup, compliance, or data management purposes.
Input parameters
The unique identifier of the conversation to delete.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DELETE_CONVAI_KNOWLEDGE_BASETool to delete a document or folder from the knowledge base. Use when you need to remove a knowledge base document or folder that is no longer needed.
Input parameters
If set to true, the document or folder will be deleted regardless of whether it is used by any agents and it will be removed from the dependent agents. For non-empty folders, this will also delete all child documents and folders.
The id of a document from the knowledge base. This is returned on document addition.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DELETE_CONVAI_KNOWLEDGE_BASE_RAG_INDEXTool to delete RAG index for a knowledge base document. Use when you need to remove semantic search indexing from a document to free up resources or when the document no longer needs to be indexed.
Input parameters
The id of RAG index of document from the knowledge base.
The id of a document from the knowledge base. This is returned on document addition.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DELETE_CONVAI_SECRETTool to delete a workspace secret if it's not in use. Use when you need to remove unused secrets from the conversational AI workspace for security or cleanup purposes.
Input parameters
The unique identifier of the workspace secret to delete. This ID is returned when creating or listing secrets.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DELETE_CONVAI_TOOLTool to delete a conversational AI tool from the workspace by ID. Use when you need to remove a tool configuration that is no longer needed or to clean up outdated tool definitions.
Input parameters
ID of the requested tool.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DELETE_DUBBING_PROJECTPermanently deletes a dubbing project by its ID; this action is irreversible and the project cannot be recovered.
Input parameters
The unique identifier for the dubbing project to be deleted. This ID is typically obtained when the dubbing project is created or listed.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DELETE_HISTORY_ITEMPermanently deletes a specific history item (including its audio file and metadata) using its `history_item_id`; this operation is irreversible and should be used with caution.
Input parameters
Unique identifier of the history item to be deleted. This ID is obtainable by listing history items, for example, via the GET `/v1/history` endpoint.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DELETE_MCP_SERVERTool to delete a specific MCP server configuration from the workspace. Use when you need to remove an MCP server that is no longer needed or to clean up outdated configurations.
Input parameters
ID of the MCP Server to delete from the workspace.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DELETE_PHONE_NUMBERTool to delete an imported phone number from the ElevenLabs workspace by ID. Use when you need to remove a phone number configuration for cleanup or to avoid stale configurations in automated environments.
Input parameters
The ID of the phone number to delete. This is returned on phone number creation.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DELETE_PROJECTUse to irreversibly delete a specific project by its `project_id`; the project must exist and be accessible, and this action cannot be undone.
Input parameters
Identifier of the project to delete. Obtain by listing projects (e.g., via GET /v1/studio/projects).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DELETE_SAMPLEPermanently deletes a specific voice sample for a given voice ID; this action is irreversible.
Input parameters
Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices.
Sample ID to be used, you can use GET https://api.elevenlabs.io/v1/voices/{voice_id} to list all the available samples for a voice.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DELETE_VOICEPermanently and irreversibly deletes a specific custom voice using its `voice_id`; the voice must exist and the authenticated user must have permission to delete it.
Input parameters
The unique identifier of the voice to be deleted.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DELETE_WORKSPACE_WEBHOOKTool to delete a specified workspace webhook by its ID. Use when you need to remove a webhook configuration that is no longer needed or to clean up webhook integrations.
Input parameters
The unique ID for the webhook
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DOWNLOAD_HISTORY_ITEMSDownloads audio clips from history by ID(s), returning a single file or a ZIP archive, with an optional output format (e.g., 'wav'); provides only audio content, no metadata.
Input parameters
Optional. Specifies the desired output audio format. Accepts 'wav' to convert the audio to WAV format. If omitted, the audio is returned in its original synthesized format (e.g., mp3). This formatting applies to each audio file, even when multiple files are downloaded and returned as a ZIP archive.
A list of unique string identifiers for the history items to be downloaded. These IDs can be obtained using the `GET /v1/history` endpoint.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DUB_A_VIDEO_OR_AN_AUDIO_FILEDub a video or audio file into a specified target language, requiring 'file' or 'source_url', 'target_lang', and 'csv_file' if 'mode' is 'manual'.
Input parameters
Video or audio file to dub. Required if 'source_url' is not provided.
Specifies dubbing mode: 'automatic' for AI-driven dubbing, or 'manual' using a .csv file for timestamped transcriptions. API defaults to 'automatic' if unspecified.
Name for the dubbing project.
CSV file with guidance for 'manual' mode dubbing. Required if 'mode' is 'manual'.
End time (seconds) for the audio portion to dub. API defaults to audio end if unspecified.
Include a watermark in the dubbed audio.
URL of the video or audio file to dub. Required if 'file' is not provided.
Start time (seconds) for the audio portion to dub. API defaults to audio start if unspecified.
Language of the original audio. Use 'auto' for automatic detection or provide a language code (e.g., 'en', 'es').
Required target language code for dubbing (e.g., 'en', 'es').
Number of speakers in the audio. Use 0 for automatic detection; otherwise, model attempts to differentiate this many speakers.
Enable Dubbing Studio features for advanced editing capabilities, if available.
Process dubbing at highest possible resolution; may increase processing time.
Background audio track for 'manual' mode with a CSV file.
Foreground audio track for 'manual' mode with a CSV file.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_DUPLICATE_CONVAI_AGENTTool to create a new agent by duplicating an existing one. Use when you need to clone an agent's configuration. The new agent will inherit all settings from the original agent but can be given a new name.
Input parameters
A name to make the agent easier to find
The id of an agent. This is returned on agent creation.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_EDIT_VOICEUpdates the name, audio files, description, or labels for an existing voice model. The voice_id must be for a voice owned by you (cloned voices). Premade/default voices cannot be edited. The 'name' field is required for all edit operations. This endpoint uses multipart/form-data format for the request body.
Input parameters
Name for the voice model. This is a required field.
Optional list of audio files to add to the voice model. Each file should be a Supported formats: mp3, wav, ogg.
JSON string of key-value pairs for categorization; new labels overwrite existing ones. Example: {"accent": "American", "gender": "male"}
Identifier of the voice to be edited; retrieve available IDs via the `/v1/voices` endpoint. Only voices owned by you can be edited.
New description for the voice model.
If set to true, will remove background noise from voice samples. Only use if samples contain background noise; using it on clean audio can reduce quality.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_EDIT_VOICE_SETTINGSEdits key voice settings (e.g., stability, similarity enhancement, style exaggeration, speaker boost) for an existing voice, affecting all future audio generated with that voice ID.
Input parameters
Controls the speech rate and pacing of the generated audio. Value typically between 0.25 and 4.0.
Adjusts the style exaggeration and expressiveness of the voice. Value between 0.0 and 1.0. Available for V2+ models. Generally recommended to keep at 0.
Identifier of the voice whose settings are to be modified. Obtain available voice IDs via the GET /v1/voices endpoint.
Controls voice consistency and randomness between generations. Value between 0.0 and 1.0. Lower values introduce broader emotional range, higher values result in more monotonous voice.
Determines how closely the AI should adhere to the original voice when attempting to replicate it. Value between 0.0 and 1.0.
Boosts the similarity to the original speaker. The differences are generally subtle. Not available for Eleven v3 model.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GENERATE_A_RANDOM_VOICEGenerates a unique, random ElevenLabs text-to-speech voice based on input text and specified voice characteristics.
Input parameters
Specifies the age category of the generated voice. Possible values are 'young', 'middle_aged', or 'old'.
The text to be synthesized into speech. The length of the text must be between 100 and 1000 characters, inclusive.
Specifies the accent of the generated voice. Accepted values include 'american', 'british', 'african', 'australian', 'indian'.
Specifies the gender of the generated voice. Possible values are 'female' or 'male'.
Controls the strength of the accent for the generated voice. Must be a numeric value between 0.3 and 2.0, inclusive.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_AGENT_DETAILSTool to retrieve available Conversational AI agents and outbound-capable Twilio phone numbers. Use when selecting an agent and phone number for outbound calls. Always reference agents by agent_id (stable identifier), not agent_name (mutable). Returns basic metadata only — conversation_config and webhook settings require a separate ConvAI agent API call. Pass agent_id and agent_phone_number_id directly to ELEVENLABS_OUTBOUND_CALL; IDs must be current and owned by the authenticated account.
Input parameters
Cursor for pagination. Used to fetch the next page of agents. Returned in previous response as next_cursor.
Maximum number of agents to return per page. Cannot exceed 100, defaults to 30.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_AGENT_LINKTool to get the current shareable link for a Conversational AI agent. Use when you need to retrieve the link URL for sharing the agent with others.
Input parameters
The id of an agent. This is returned on agent creation.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_A_PROFILE_PAGERetrieves the profile information for the authenticated ElevenLabs user (identified by API key).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_AUDIO_FROM_HISTORY_ITEMRetrieves the audio content for a specific history item from ElevenLabs, using a `history_item_id` that must correspond to a previously generated audio.
Input parameters
The unique identifier for the history item. This ID can be obtained by listing your history items (e.g., via an action that calls GET /v1/history).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_AUDIO_FROM_SAMPLERetrieves the audio for a given `sample_id` that must belong to the specified `voice_id`.
Input parameters
Identifier for the voice. A list of available voice IDs can be obtained from the GET https://api.elevenlabs.io/v1/voices endpoint.
Identifier for the sample. A list of available sample IDs for a specific voice can be obtained from the GET https://api.elevenlabs.io/v1/voices/{voice_id} endpoint.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_AUDIO_NATIVE_SETTINGSTool to retrieve player settings for a specific Audio Native project. Use when you need to check the current configuration of an audio-native project, including display settings, colors, and status.
Input parameters
The ID of the Studio project. Use the audio-native project ID from when you created the project.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CHAPTER_BY_IDFetches comprehensive details for a specific chapter within a given project, including its metadata (name, ID), conversion status, progress, download availability, and content statistics.
Input parameters
Identifier of the chapter. You can find `chapter_id` by listing all available chapters for a project via the `/v1/studio/projects/{project_id}/chapters` endpoint.
Identifier of the project. You can find `project_id` by listing all available projects via the `/v1/studio/projects` endpoint.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CHAPTERSRetrieves a list of all chapters, their details, and conversion status for a project, useful for managing content or tracking progress.
Input parameters
Identifier of the Studio project for which to retrieve chapters. You can find available `project_id`s by listing all projects (e.g., via GET https://api.elevenlabs.io/v1/studio/projects).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CHAPTER_SNAPSHOTSRetrieves all saved version snapshots for a specific chapter within a given project, enabling review of its history or reversion to prior states.
Input parameters
Identifier of the chapter for which snapshots are to be retrieved.
Identifier of the project containing the chapter.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_AGENTTool to retrieve the complete configuration for a specific Conversational AI agent by ID. Use when you need to inspect or audit an agent's settings, workflow, conversation config, or assigned channels.
Input parameters
The ID of the agent. This is returned on agent creation.
The ID of the branch to use. If not specified, uses the main branch.
The ID of the agent version to use. If not specified, uses the latest version.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_AGENT_KNOWLEDGE_BASE_SIZETool to retrieve the number of pages in a conversational AI agent's knowledge base. Use when you need to check the size of an agent's knowledge base content.
Input parameters
The unique identifier of the conversational AI agent.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_AGENTS_SUMMARIESTool to retrieve summaries for specified Conversational AI agents. Use when you need to fetch metadata such as name, tags, creation time, access level, and archival status for one or more agents.
Input parameters
List of agent IDs to fetch summaries for. At least one agent ID is required.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_AGENTS_WIDGETTool to retrieve the widget configuration for a Conversational AI agent. Use when you need to fetch display settings, colors, text content, and behavior options for an agent's embedded widget.
Input parameters
The id of an agent. This is returned on agent creation.
An expiring token that enables a websocket conversation to start. These can be generated for an agent using the /v1/convai/conversation/get-signed-url endpoint
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_AGENT_TESTING_BY_IDTool to retrieve an ElevenLabs Conversational AI agent response test by its ID. Use when you need to fetch details of a specific test including its configuration, type, and test parameters.
Input parameters
The id of a chat response test. This is returned on test creation.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_ANALYTICS_LIVE_COUNTTool to retrieve the live count of active ongoing Conversational AI conversations. Use when monitoring real-time conversation activity or checking current load.
Input parameters
The id of an agent to restrict the analytics to. If not provided, returns analytics across all agents.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_BATCH_CALLINGTool to get detailed information about a batch call including all recipients. Use when you need to check the status, progress, or results of a previously submitted batch calling job.
Input parameters
The unique identifier of the batch call to retrieve.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_BATCH_CALLING_WORKSPACETool to retrieve all batch calls for the current workspace. Use when you need to list all batch calling campaigns, check their status, or find specific batch calls by name or agent.
Input parameters
Maximum number of batch calls to return per page.
Document ID for pagination. Use the 'next_doc' value from a previous response to get the next page of results.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_CONVERSATIONSTool to retrieve all conversations of agents that user owns. Use when you need to list conversations, optionally filtered by agent, time range, duration, rating, or other criteria. Supports pagination via cursor.
Input parameters
Used for fetching next page. Cursor is returned in the response.
Full-text or fuzzy search over transcript messages.
Filter conversations by the user ID who initiated them.
The id of the agent you're taking the action on. Use this to restrict results to a specific agent.
Filter conversations by branch ID.
How many conversations to return at maximum. Can not exceed 100, defaults to 30.
Maximum overall rating (1-5).
Minimum overall rating (1-5).
Filter conversations by tool names used during the call.
Summary mode for conversation responses.
Filter conversations by detected main language (language code).
The result of the success evaluation. Filter by success status.
Evaluation filters. Supports multiple values (repeated query params). Format per value: criteria_id:result. Example: \['value_framing:success', 'tone:professional'\]
Filter conversations with user feedback comments.
Unix timestamp (in seconds) to filter conversations after to this start date.
Maximum call duration in seconds.
Minimum call duration in seconds.
Unix timestamp (in seconds) to filter conversations up to this start date.
Data collection filters. Supports multiple values (repeated query params). Format per value: id:op:value where op is one of eq\\ | neq\\ | gt\\ | gte\\ | lt\\ | lte\\ | in\\ | exists\\ | missing. For in, pipe-delimit values.
Filter conversations by initiation source.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_KNOWLEDGE_BASETool to retrieve a list of available knowledge base documents. Use when you need to browse, search, or filter knowledge base documents by name, type, folder, or ownership. Supports pagination via cursor for large result sets.
Input parameters
If present, the endpoint will return only documents of the given types.
Used for fetching next page. Cursor is returned in the response.
If specified, the endpoint returns only such knowledge base documents whose names start with this string.
The field to sort the results by.
How many documents to return at maximum. Can not exceed 100, defaults to 30.
Whether folders should be returned first in the list of documents.
Sort direction for knowledge base documents.
If set, the endpoint will return only documents that are direct children of the given folder.
If set, the endpoint will return only documents that are descendants of the given folder.
If set to true, the endpoint will return only documents owned by you (and not shared from somebody else).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_KNOWLEDGE_BASE_CONTENTTool to retrieve the entire content of a document from the knowledge base. Use when you need to access or read the full text content of a knowledge base document.
Input parameters
The id of a document from the knowledge base. This is returned on document addition.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_KNOWLEDGE_BASE_DEPENDENT_AGENTSTool to retrieve a list of agents depending on a specific knowledge base document. Use when you need to identify which agents are using a particular document, either directly or transitively.
Input parameters
Used for fetching next page. Cursor is returned in the response.
How many documents to return at maximum. Can not exceed 100, defaults to 30.
Type of dependent agents to return.
The id of a document from the knowledge base. This is returned on document addition.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_KNOWLEDGE_BASE_DOCUMENTATIONTool to get details about a specific documentation making up the agent's knowledge base. Use when you need to retrieve information about a knowledge base document, including its content, type, and metadata.
Input parameters
Optional agent ID to scope the knowledge base query
The id of a document from the knowledge base. This is returned on document addition.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_KNOWLEDGE_BASE_RAG_INDEXTool to retrieve RAG index overview including total size and usage information. Use when you need to check storage limits, monitor usage, or understand which embedding models are consuming space in knowledge base documents.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_KNOWLEDGE_BASE_RAG_INDEXESTool to retrieve all RAG indexes for a specified knowledge base document. Use when you need to view the indexing status, models used, and usage statistics for a document's semantic search capabilities.
Input parameters
The id of a document from the knowledge base. This is returned on document addition.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_KNOWLEDGE_BASE_SOURCE_FILE_URLTool to get a signed URL to download the original source file of a file-type document from the knowledge base. Use when you need to download the original file that was uploaded to create a knowledge base document.
Input parameters
The id of a document from the knowledge base. This is returned on document addition.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_KNOWLEDGE_BASE_SUMMARIESTool to retrieve knowledge base document summaries by their IDs. Use when you need to get summaries for multiple knowledge base documents in a single request.
Input parameters
The IDs of knowledge base documents to retrieve summaries for.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_MCP_SERVERTool to retrieve a specific MCP server configuration from the workspace. Use when you need to inspect details of an existing MCP server including its URL, transport type, approval policies, and dependent agents.
Input parameters
ID of the MCP Server.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_MCP_SERVERSTool to retrieve all MCP (Model Context Protocol) server configurations available in the workspace. Use when you need to list all registered MCP servers or check which servers are available for conversational AI agents.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_MCP_SERVER_TOOLSTool to retrieve all tools available for a specific MCP server configuration. Use when you need to inspect what tools an MCP server provides or verify tool availability before using them.
Input parameters
ID of the MCP Server.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_PHONE_NUMBER_BY_IDTool to retrieve detailed configuration for a specific phone number by ID. Use when you need to inspect a phone number's provider details, capabilities, agent assignments, or SIP trunk configuration.
Input parameters
The ID of the phone number. This is returned on phone number creation.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_SECRETSTool to retrieve all workspace secrets for the user. Use when you need to list stored secrets that can be used for authentication and integration with conversational AI agents. Supports pagination.
Input parameters
Used for fetching next page. Cursor is returned in the response.
How many secrets to return at maximum. Can not exceed 100. If not provided, returns all secrets.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_SETTINGSTool to retrieve Convai settings for the workspace. Use when you need to inspect webhook configurations, RAG retention settings, or MCP server capabilities.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_SETTINGS_DASHBOARDTool to retrieve Convai dashboard settings for the workspace. Use when you need to inspect configured dashboard charts for monitoring conversational AI performance.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_TEST_INVOCATIONSTool to list all test invocations for a specific conversational AI agent with pagination support. Use when you need to retrieve test invocation history, check test results, or paginate through large sets of test runs.
Input parameters
Cursor for pagination. Use the next_cursor value from a previous response to fetch the next page of results.
Filter test invocations by agent ID. This is required to fetch test invocations for a specific agent.
How many test invocations to return at maximum. Cannot exceed 100. Defaults to 30 if not specified.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_TOOLTool to retrieve the complete configuration for a specific conversational AI tool by ID. Use when you need to inspect a tool's settings, type, or usage statistics from the workspace.
Input parameters
ID of the requested tool.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_TOOLSTool to retrieve all available tools in the workspace. Use when you need to list, search, or discover tools that can be used with Conversational AI agents.
Input parameters
Filter tools by type. Comma-separated list of tool types.
Cursor for pagination. Used to fetch the next page of results.
Filter tools whose names start with this string.
The field to sort the results by.
How many tools to return at maximum. Cannot exceed 100, defaults to 30.
Sort direction options for listing tools.
If set to true, return only tools owned by you (not shared from others).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVAI_TOOLS_DEPENDENT_AGENTSTool to retrieve a list of agents depending on a specific tool. Use when you need to identify which agents are using a particular tool in their configuration.
Input parameters
Used for fetching next page. Cursor is returned in the response.
ID of the requested tool.
How many documents to return at maximum. Can not exceed 100, defaults to 30.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVERSATION_BY_IDTool to fetch full details for a single Conversational AI conversation by ID. Use when you need transcript-level analysis, metadata, or audio status flags for a specific conversation.
Input parameters
The unique identifier of the conversation to retrieve.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_CONVERSATION_SIGNED_URLTool to get a signed URL to start a conversation with an agent that requires authorization. Use when you need to obtain a secure WebSocket URL for initiating a conversation session.
Input parameters
The id of the agent you're taking the action on.
The ID of the branch to use
Whether to include a conversation_id with the response. If included, the conversation_signature cannot be used again.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_DEFAULT_VOICE_SETTINGSRetrieves the ElevenLabs text-to-speech service's default voice settings (stability, similarity boost, style, speaker boost) that are applied when no voice-specific or request-specific settings are provided.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_DUBBED_FILERetrieves an existing dubbed audio file for a specific `dubbing_id` and `language_code`.
Input parameters
The unique identifier for the dubbing project from which to retrieve the audio.
The language code specifying the desired language of the dubbed audio file (e.g., 'en', 'es', 'de-DE').
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_DUBBING_PROJECT_METADATARetrieves metadata and status for a specific dubbing project by its ID.
Input parameters
The unique identifier of the dubbing project whose metadata is to be retrieved.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_DUBBING_TRANSCRIPTS_FORMATRetrieves the transcript for a specific dubbing project and language in the requested format (SRT, WebVTT, or JSON). Use this when you need subtitles or detailed transcript data with timing information for a dubbed video or audio.
Input parameters
ID of the dubbing project.
Format to return transcript in. For subtitles use either 'srt' or 'webvtt', and for a full transcript use 'json'. The 'json' format is not yet supported for Dubbing Studio.
ISO-693 language code to retrieve the transcript for. Use 'source' to fetch the transcript of the original media.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_GENERATED_ITEMSRetrieves metadata for a list of generated audio items from history, supporting pagination and optional filtering by voice ID.
Input parameters
Filters the history items to only include those generated with the specified voice ID. You can obtain voice IDs by listing available voices (e.g., using an action to get voices from `https://api.elevenlabs.io/v1/voices`).
Specifies the maximum number of history items to return per page. The value must be between 1 and 1000, inclusive.
The ID of the history item to start fetching results after, for pagination. If not provided, items are fetched from the most recent, ordered by creation date in descending order.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_HISTORY_ITEM_BY_IDRetrieves detailed information (excluding the audio file) for a specific audio generation history item from ElevenLabs, using its unique ID.
Input parameters
Unique identifier of the history item to retrieve.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_MCP_TOOL_CONFIGTool to retrieve configuration overrides for a specific MCP tool within an MCP server. Use when you need to inspect the custom execution settings for individual tools.
Input parameters
Name of the MCP tool to retrieve config overrides for
ID of the MCP Server
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_METADATA_FOR_A_PRONUNCIATION_DICTIONARYRetrieves metadata for a specific, existing pronunciation dictionary from ElevenLabs using its ID.
Input parameters
The unique identifier of the pronunciation dictionary for which to retrieve metadata.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_MODELSRetrieves a detailed list of all available ElevenLabs text-to-speech (TTS) models and their capabilities.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_PROJECT_BY_IDUse to retrieve all details for a specific project, including its chapters and their conversion statuses, by providing the project's unique ID.
Input parameters
Unique identifier for the project. To list all available projects and their IDs, you can use the endpoint that lists all projects (e.g., GET /v1/projects).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_PROJECTSFetches a list of all projects and their details associated with the user's ElevenLabs account; this is a read-only operation.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_PROJECT_SNAPSHOTSRetrieves all available snapshots (saved states or versions) for an existing project, enabling history tracking, version comparison, or accessing specific states for playback/processing, particularly in text-to-speech workflows.
Input parameters
Identifier of the project for which to retrieve snapshots. You can obtain project_ids by querying the GET /v1/studio/projects endpoint to list all available projects.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_PRONUNCIATION_DICTIONARIESRetrieves a paginated list of pronunciation dictionaries, used to customize how specific words or phrases are pronounced by the text-to-speech (TTS) engine.
Input parameters
Cursor for pagination, obtained from a previous response, to fetch the next set of pronunciation dictionaries. Omit or leave empty to retrieve the first page.
The number of pronunciation dictionaries to retrieve per page, with a maximum value of 100.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_PRONUNCIATION_DICT_VERSIONDownloads the Pronunciation Lexicon Specification (PLS) file for an existing version of a pronunciation dictionary from ElevenLabs, used to customize TTS pronunciation.
Input parameters
The unique identifier of the specific version of the pronunciation dictionary.
The unique identifier of the pronunciation dictionary.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_SERVICE_ACCOUNTSTool to list all service accounts in the workspace. Use when you need to view service accounts, their associated API keys, or manage workspace access.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_SHARED_VOICESRetrieves a paginated and filterable list of shared voices from the ElevenLabs Voice Library.
Input parameters
Filters voices by age group.
Page number for pagination, starting from 0.
Valid sort options for shared voices.
Filters voices by accent.
Filters voices by gender.
A search term to filter voices by name or description.
Filters voices by category.
Filters for voices that are marked as featured.
Filters voices by language (ISO 639-1 code).
Filters voices by the public ID of their owner.
Maximum number of shared voices per page (max 100).
Filters voices by their intended use cases.
Filters voices by descriptive tags.
Filters for voices that are enabled for the reader application.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_SSO_PROVIDER_ADMINRetrieves the SSO provider configuration for a specified workspace, typically for review purposes, and will indicate if no configuration exists.
Input parameters
The unique identifier of the workspace for which to retrieve the SSO provider configuration.
The admin URL prefix for the workspace. This is typically 'v1' for the standard API version.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_SUMMARIES_CONVAI_AGENT_TESTING_SUMMARIESTool to retrieve multiple agent response test summaries by their IDs. Use when you need to fetch summary information for multiple tests in a single request. Returns a dictionary mapping test IDs to their summary details including name, type, and timestamps.
Input parameters
List of test IDs to fetch. No duplicates allowed.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_TRANSCRIPT_FOR_DUBRetrieves the textual transcript for a specified dubbing project and language, if one exists for that language in the project.
Input parameters
The unique identifier for the dubbing project.
The ISO 639-1 language code for which to retrieve the transcript.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_USAGE_CHARACTER_STATSTool to retrieve usage metrics for the current user or entire workspace. Returns time-series data with configurable aggregation intervals and breakdown types. Use when analyzing character usage patterns, tracking consumption by voice, user, or other dimensions over time.
Input parameters
Which metric to aggregate.
UTC Unix timestamp for the end of the usage window, in milliseconds. To include the last day of the window, the timestamp should be at 23:59:59 of that day.
UTC Unix timestamp for the start of the usage window, in milliseconds. To include the first day of the window, the timestamp should be at 00:00:00 of that day.
Breakdown type for usage statistics.
Aggregation interval for usage data over time.
Aggregation bucket size in seconds. Overrides the aggregation interval.
Whether or not to include the statistics of the entire workspace. Default is false.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_USER_INFORetrieves detailed information about the authenticated ElevenLabs user's account, including subscription, usage, API key, and status.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_USER_SUBSCRIPTION_INFORetrieves detailed subscription information for the currently authenticated ElevenLabs user.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_VOICERetrieves comprehensive details for a specific, existing voice by its `voice_id`, optionally including its settings.
Input parameters
Identifier of the voice. Use the `GET /v1/voices` endpoint to list available IDs.
If true, the response will include detailed settings information for the voice.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_VOICESRetrieves a list of all available voices along with their detailed attributes and settings.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_VOICE_SETTINGSRetrieves the stability, similarity, style, and speaker boost settings for a specific, existing ElevenLabs voice using its `voice_id`.
Input parameters
Identifier of the voice for which to retrieve settings. A list of available voice IDs can be obtained from the /v1/voices endpoint.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_WORKSPACE_RESOURCETool to get metadata of a workspace resource by ID and type. Use when you need access control information, creator details, or sharing options for a specific resource.
Input parameters
The ID of the target resource.
Resource type of the target resource.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_GET_WORKSPACE_WEBHOOKSTool to list all webhooks configured for the workspace. Use when you need to view existing webhook configurations or verify webhook settings.
Input parameters
Whether to include active usages of the webhook, only usable by admins
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_LIST_CONVAI_AGENT_TESTINGTool to list all agent response tests with pagination support and optional search filtering. Use when you need to retrieve available tests, search tests by name, or paginate through large test collections.
Input parameters
Used for fetching next page. Cursor is returned in the response.
Search query to filter tests by name.
How many tests to return at maximum. Cannot exceed 100, defaults to 30.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_LIST_DUBSTool to list dubbing projects you have access to. Use when you need to retrieve dubs, check their status, or paginate through available dubbing projects.
Input parameters
Cursor for pagination. Use the next_cursor value from a previous response to fetch the next page.
The field to use for ordering results from this query.
Number of dubs to return per page. Cannot exceed 200, defaults to 100.
Status of the dubbing project.
Order direction for results.
Filter for who created the dubbing projects.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_LIST_PHONE_NUMBERSTool to list all imported phone numbers in the workspace. Use when you need to find available phone numbers, check their capabilities (inbound/outbound), or verify which agent is assigned to a number.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_LIST_WHATSAPP_ACCOUNTSTool to list all WhatsApp accounts in the workspace. Use when you need to view available WhatsApp Business accounts, check which agents are assigned to WhatsApp numbers, or retrieve WhatsApp phone number details.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_MOVE_BULK_CONVAI_KNOWLEDGE_BASETool to move multiple documents or folders from one folder to another in the knowledge base. Use when you need to reorganize multiple knowledge base items at once by moving them to a different folder or to the root level.
Input parameters
The folder ID to move the entities to. If not set, the entities will be moved to the root folder.
The ids of documents or folders from the knowledge base to move. Must contain between 1 and 20 IDs.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_MOVE_CONVAI_KNOWLEDGE_BASETool to move a knowledge base document or folder to a different folder. Use when you need to reorganize your knowledge base by moving entities between folders or to the root level.
Input parameters
The folder to move the entities to. If not set, the entities will be moved to the root folder.
The id of a document from the knowledge base. This is returned on document addition.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_OUTBOUND_CALLTool to place an outbound call via SIP trunk. Use when you need to initiate a voice call through an ElevenLabs agent after obtaining required IDs. Prerequisites: - The API key must have Conversational AI (convai) permissions enabled. For write operations like initiating calls, ensure your API key has the appropriate convai write scope. - A valid SIP trunk phone number must be configured for outbound calls in ElevenLabs. - The SIP trunk must have valid outbound configuration with proper address and credentials. - The agent must be properly configured in the Conversational AI platform.
Input parameters
Agent ID to place the call with (retrieve via Agents API).
Destination phone number in E.164 format to call.
ID of the phone number to originate the call from (must support outbound calls).
Personalization and override payload for initiating a conversation.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_REDIRECT_TO_MINTLIFYRetrieves the content of the official ElevenLabs API documentation page hosted on Mintlify.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_REGISTER_CALL_CONVAI_TWILIOTool to register a Twilio call and return TwiML to connect the call to an ElevenLabs Conversational AI agent. Use when you need to integrate ElevenLabs agents with your own Twilio infrastructure for inbound or outbound calls.
Input parameters
The unique identifier of the Conversational AI agent to use for this call
Direction of the call: 'inbound' for incoming calls or 'outbound' for outgoing calls
The phone number the call is directed to in E.164 format
The phone number the call is originating from in E.164 format
Optional client data for conversation initialization.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_REMOVE_RULES_FROM_THE_PRONUNCIATION_DICTIONARYPermanently removes exact-match pronunciation rules from a specified ElevenLabs pronunciation dictionary using a list of rule strings; non-matching rule strings are ignored and this action cannot add or modify rules.
Input parameters
A list of exact pronunciation rule strings to be removed from the dictionary (e.g., 'word -> wɜːd'). Non-matching strings will be ignored.
Identifier of the pronunciation dictionary from which rules will be removed.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_RESUBMIT_CONVAI_TEST_INVOCATIONSTool to resubmit specific test runs from a test invocation for a conversational AI agent. Use when you need to re-run failed tests or specific test cases from a previous test invocation.
Input parameters
Agent ID to resubmit tests for
ID of the branch to run the tests on. If not provided, the tests will be run on the agent default configuration.
List of test run IDs to resubmit
The id of a test invocation. This is returned when tests are run.
Configuration overrides to use for testing. If not provided, the agent's default configuration will be used.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_RETRY_CONVAI_BATCH_CALLTool to retry a batch call, calling failed and no-response recipients again. Use when you need to retry unsuccessful calls from a previous batch calling campaign.
Input parameters
Unique identifier of the batch call to retry. Retries failed and no-response recipients.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_RUN_AGENT_TESTSTool to run selected tests on a conversational AI agent with optional configuration overrides. Use when you need to execute automated tests on an agent to validate responses, tool calls, or conversation flows. Supports running up to 200 tests in a single invocation with optional branch-specific or configuration override testing.
Input parameters
List of tests to run on the agent. Must contain at least 1 test and at most 200 tests.
The unique identifier of the agent to run tests on. This is returned on agent creation.
ID of the branch to run the tests on. If not provided, the tests will be run on the agent default configuration.
Configuration overrides to use for testing.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_SET_AGENT_AVATARTool to set or update the avatar image for a Conversational AI agent displayed in the widget. Use when you need to customize the visual appearance of an agent by uploading a profile image.
Input parameters
The unique identifier of the agent. This is returned on agent creation.
Image file to be used as the agent's avatar.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_SIMULATE_CONVAI_AGENTS_SIMULATE_CONVERSATIONTool to run a simulated conversation between an agent and an AI user. Use when testing agent behavior with specific scenarios or evaluating conversation flow. Returns full transcript with analysis including success metrics and conversation summary.
Input parameters
The id of an agent. This is returned on agent creation.
Maximum number of new turns to generate in the conversation simulation
A specification that will be used to simulate a conversation between an agent and an AI user
A list of evaluation criteria to test
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_SPEECH_TO_SPEECHConverts an input audio file to speech using a specified voice; if a `model_id` is provided, it must support speech-to-speech conversion.
Input parameters
Seed for deterministic audio generation (integer 0-4294967295). Same seed and parameters yield same audio.
The audio file to be converted.
Identifier of the model. Must support speech-to-speech (where `can_do_voice_conversion` is true). Use /v1/models to list models.
Identifier of the voice to be used. Available voices can be retrieved using the /v1/voices endpoint.
Output audio format. Supported options: mp3_22050_32 (MP3 22.05kHz, 32kbps), mp3_44100_32 (MP3 44.1kHz, 32kbps), mp3_44100_64 (MP3 44.1kHz, 64kbps), mp3_44100_96 (MP3 44.1kHz, 96kbps), mp3_44100_128 (MP3 44.1kHz, 128kbps), mp3_44100_192 (MP3 44.1kHz, 192kbps; Requires Creator tier or above), pcm_16000 (PCM S16LE 16kHz), pcm_22050 (PCM S16LE 22.05kHz), pcm_24000 (PCM S16LE 24kHz), pcm_44100 (PCM S16LE 44.1kHz; Requires Pro tier or above), ulaw_8000 (μ-law 8kHz; for Twilio audio inputs).
JSON string defining voice settings, such as `stability` (float) and `similarity_boost` (float).
Latency optimization. Higher values reduce latency but may lower quality. Options: 0 (no optimizations), 1 (normal), 2 (strong), 3 (max), 4 (max, text normalizer disabled; best latency, can mispronounce numbers/dates).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_SPEECH_TO_SPEECH_STREAMINGConverts an input audio stream to a different voice output stream in real-time, using a specified speech-to-speech model.
Input parameters
An integer seed for deterministic audio generation (0-4294967295). Using the same seed with identical input parameters aims to produce the same audio output, aiding reproducibility.
The input audio file (e.g..wav.mp3) to be converted.
Identifier of the speech-to-speech model (e.g., 'eleven_english_sts_v2'). Ensure the chosen model supports voice conversion. Available models can be fetched from the `/v1/models` endpoint.
Identifier for the voice to be used. A list of available voices can be fetched from the `https://api.elevenlabs.io/v1/voices` endpoint.
Desired output audio stream format. Supported formats include: 'mp3_22050_32': MP3 22.05kHz 32kbps. 'mp3_44100_32': MP3 44.1kHz 32kbps. 'mp3_44100_64': MP3 44.1kHz 64kbps. 'mp3_44100_96': MP3 44.1kHz 96kbps. 'mp3_44100_128': MP3 44.1kHz 128kbps. 'mp3_44100_192': MP3 44.1kHz 192kbps (requires Creator tier or above). 'pcm_16000': PCM (S16LE) 16kHz. 'pcm_22050': PCM (S16LE) 22.05kHz. 'pcm_24000': PCM (S16LE) 24kHz. 'pcm_44100': PCM (S16LE) 44.1kHz (requires Pro tier or above). 'ulaw_8000': μ-law 8kHz (commonly used for Twilio audio inputs).
A JSON string containing voice settings, such as stability and similarity_boost, to fine-tune the characteristics of the generated voice. Example: '{"stability": 0.5, "similarity_boost": 0.75}'. If not provided, the default voice settings for the selected voice will be used.
Controls latency optimizations for streaming audio. Higher values offer lower latency at a potential cost to audio quality. Supported values: 0: Default mode (no latency optimizations). 1: Normal latency optimizations (provides about 50% of the latency improvement of option 3). 2: Strong latency optimizations (provides about 75% of the latency improvement of option 3). 3: Maximum latency optimizations. 4: Maximum latency optimizations, with text normalizer turned off (can mispronounce numbers and dates but offers the best latency).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_STREAM_AUDIO_ISOLATIONTool to remove background noise from audio and stream the isolated result. Use when you need to clean up audio recordings by isolating vocals/speech and removing unwanted background noise. The audio file must be at least 4.6 seconds long.
Input parameters
The audio file from which vocals/speech will be isolated. Audio must be at least 4.6 seconds long.
The format of input audio. Use 'pcm_s16le_16' for 16-bit PCM at a 16kHz sample rate, single channel (mono), and little-endian byte order (lower latency). Use 'other' for all other encoded waveform formats.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_STREAM_CHAPTER_AUDIOStreams the audio for a specified chapter snapshot from an ElevenLabs project, optionally converting the output to MPEG format.
Input parameters
Identifier of the chapter. To list available chapters for a specific project, use the GET /v1/studio/projects/{project_id}/chapters endpoint.
Identifier of the project. To find available project IDs, you can list all projects using the GET /v1/studio/projects endpoint.
If true, the output audio stream will be converted to MPEG format. If false, the audio will be streamed in its original format (likely PCM).
Identifier of the chapter snapshot (a specific version of the chapter). To list all available snapshots for a chapter, use the GET /v1/studio/projects/{project_id}/chapters/{chapter_id}/snapshots endpoint.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_STREAM_CONVAI_AGENTS_SIMULATE_CONVERSATIONTool to run a simulated conversation between an agent and a simulated user, streaming back the response. Response is streamed as partial lists of messages that should be concatenated, with a final message containing conversation analysis once complete.
Input parameters
The ID of the conversational AI agent. This is returned on agent creation.
Maximum number of new turns to generate in the conversation simulation.
Specification that defines how to simulate the conversation between the agent and a simulated user.
A list of additional evaluation criteria to test during the simulation.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_STREAM_PROJECT_AUDIOStreams audio from a specific project snapshot, optionally converting it to MPEG format.
Input parameters
Identifier of the project.
If true, converts the output audio to MPEG format; otherwise, streams in its original or a default raw format.
Identifier of the project snapshot.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_STREAMS_ARCHIVE_WITH_PROJECT_AUDIOArchives an existing project snapshot by its ID, creating a permanent, immutable, and typically irreversible copy of its state.
Input parameters
The ID of the project whose snapshot is to be archived.
The ID of the project snapshot to archive.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_SUBMIT_BATCH_CALLTool to submit a batch call. Use when you need to initiate multiple calls (voice or WhatsApp) at once. Triggers real outbound calls immediately (if no scheduled_time_unix is set) or at the scheduled time — always confirm recipient list and call count with the user before executing.
Input parameters
ID of the agent to use for the calls
Name of the batch call
List of recipient objects for batch calling
Unix timestamp to schedule the batch (omit or null to send immediately)
ID of the phone number to originate calls from
ID of the WhatsApp Business Account to use
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_TEXT_TO_SPEECHConverts text to speech using a specified ElevenLabs voice and model, returning a downloadable audio file (use ELEVENLABS_TEXT_TO_SPEECH_STREAM for streaming instead). Audio URL is nested at `data.file.s3url` in the response. Keep `voice_id`, `model_id`, and `output_format` consistent across all chunks to avoid audible artifacts when concatenating. Some voice/model/format combinations require specific subscription tiers; test with a short sample before full runs. HTTP 429 on burst batches; respect `Retry-After` headers.
Input parameters
Integer seed for potentially deterministic audio generation. Repeatability with the same seed and parameters is aimed for but not guaranteed.
Input text for speech conversion. Max 10,000 characters for most models. Flash/Turbo v2 models: up to 30,000. Flash/Turbo v2.5 models: up to 40,000. For long-form content, use Studio.
Identifier of the model for synthesis. List available models via `/v1/models`; ensure chosen model's `can_do_text_to_speech` is true.
Identifier of the voice for speech generation. Obtainable from the `/v1/voices` endpoint.
Output audio format. Supported formats include: - `mp3_22050_32`: 22.05kHz, 32kbps MP3. - `mp3_44100_32`: 44.1kHz, 32kbps MP3. - `mp3_44100_64`: 44.1kHz, 64kbps MP3. - `mp3_44100_96`: 44.1kHz, 96kbps MP3. - `mp3_44100_128`: 44.1kHz, 128kbps MP3. - `mp3_44100_192`: 44.1kHz, 192kbps MP3 (Creator tier+). - `pcm_16000`: 16kHz PCM (S16LE). - `pcm_22050`: 22.05kHz PCM (S16LE). - `pcm_24000`: 24kHz PCM (S16LE). - `pcm_44100`: 44.1kHz PCM (S16LE) (Pro tier+). - `ulaw_8000`: 8kHz μ-law (for Twilio audio inputs).
Voice settings for controlling speech generation characteristics.
Controls latency optimizations for streaming. Higher values reduce latency, potentially affecting quality. 0: No optimizations. 1: Normal (approx. 50% of max improvement vs option 3). 2: Strong (approx. 75% of max improvement vs option 3). 3: Maximum. 4: Maximum with text normalizer disabled (affects number/date pronunciation, best latency). NOTE: Not supported with model 'eleven_v3'. If using eleven_v3, leave this parameter unset.
List of up to 3 pronunciation dictionary locators, applied sequentially. Each dictionary must contain `pronunciation_dictionary_id` and `version_id`.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_TEXT_TO_SPEECH_STREAMConverts text to a spoken audio stream (no saved file or history entry); use the non-streaming text-to-speech tool when a persistent audio URL is needed. Allows latency optimization, specific output formats (some tier-dependent), and custom pronunciations; ensure the chosen model supports text-to-speech and text is preferably under 5000 characters. Keep voice_id, model_id, and output_format consistent across multi-chunk sessions to avoid audio artifacts.
Input parameters
If specified, the system will attempt to sample deterministically, meaning that repeated requests with the same seed and parameters should ideally return the same audio result. However, complete determinism is not guaranteed.
The text that will be converted into speech. It is recommended to keep the text length under 5000 characters, as longer texts might face limitations.
Identifier of the model to be used for text-to-speech conversion. Available models can be listed using the `GET /v1/models` endpoint. Ensure the chosen model supports text-to-speech by verifying its `can_do_text_to_speech` property. Voice and account compatibility with specific models (e.g., eleven_turbo_v2, eleven_multilingual_v2) may vary; validate by testing a short clip (~200 characters) before full runs.
Identifier of the voice to be used for speech generation. A list of available voice IDs can be retrieved from the `GET /v1/voices` endpoint.
Specifies the desired output format for the generated audio stream. Supported MP3 formats: - mp3_22050_32: MP3, 22.05kHz, 32kbps. - mp3_44100_32: MP3, 44.1kHz, 32kbps. - mp3_44100_64: MP3, 44.1kHz, 64kbps. - mp3_44100_96: MP3, 44.1kHz, 96kbps. - mp3_44100_128: MP3, 44.1kHz, 128kbps. - mp3_44100_192: MP3, 44.1kHz, 192kbps (Creator tier or above required). Supported PCM formats (S16LE): - pcm_16000: PCM, 16kHz. - pcm_22050: PCM, 22.05kHz. - pcm_24000: PCM, 24kHz. - pcm_44100: PCM, 44.1kHz (Pro tier or above required). Supported μ-law format: - ulaw_8000: μ-law, 8kHz (commonly used for Twilio audio inputs).
Controls latency optimization for the streaming audio. Higher values prioritize lower latency, potentially at the cost of audio quality. Possible values: - 0: Default mode (no latency optimizations). - 1: Normal latency optimizations (reduces latency by approximately 50% of option 3's improvement). - 2: Strong latency optimizations (reduces latency by approximately 75% of option 3's improvement). - 3: Maximum latency optimizations. - 4: Maximum latency optimizations with text normalizer disabled (offers the lowest latency but may lead to mispronunciations of numbers, dates, etc.).
A list of pronunciation dictionary locators to be applied to the text. Each locator should be a dictionary containing 'pronunciation_dictionary_id' (string) and 'version_id' (string). Dictionaries are applied in the provided order. A maximum of 3 locators can be used per request.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_UPDATE_AUDIO_NATIVE_CONTENTTool to update content for an Audio Native project by uploading a text or HTML file. Use when you need to refresh or change the content of an existing Audio Native project. Optionally auto-convert to audio and auto-publish the new snapshot.
Input parameters
Text or HTML file containing the article content. For HTML, format as '<html><body><div><p>Your content</p><h5>More content</h5></div></body></html>'.
The ID of the Audio Native project to update.
Whether to automatically convert the project to audio after updating content.
Whether to automatically publish the new project snapshot after conversion completes.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_UPDATE_CONVAI_AGENTTool to update an existing ElevenLabs Conversational AI agent's settings. Use when you need to modify an agent's configuration, such as changing its name, conversation settings, workflow, or platform settings.
Input parameters
A name to make the agent easier to find
Tags to help classify and filter the agent
The id of an agent. This is returned on agent creation.
Workflow configuration defining conditional logic, tool execution modes, and conversation flow patterns for the agent
The ID of the branch to use
List of procedure refs used for this agent version.
Platform settings for the agent are all settings that aren't related to the conversation orchestration and content.
Conversation configuration for an agent
Description for this version when publishing changes (only applicable for versioned agents)
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_UPDATE_CONVAI_AGENT_TESTINGTool to update an existing ElevenLabs Conversational AI agent response test by ID. Use when you need to modify test configuration, chat history, success conditions, or other test parameters.
Input parameters
Name for the test case to identify it later
Type of agent test.
The id of a chat response test. This is returned on test creation.
Array of messages representing the conversation history to test against. Each message must include role ('user' or 'agent'), time_in_call_secs (float), and optional message text content.
Examples of failed or incorrect agent responses for LLM tests
Examples of successful agent responses for LLM tests
Key-value pairs of variables to be dynamically injected into the test context
For 'llm' and 'simulation' types: Natural language description of what constitutes a successful agent response
For 'simulation' type: Natural language description of the scenario to simulate in the conversation
For 'simulation' type tests: Maximum number of conversation turns to simulate
For 'tool_call' type tests: Expected parameters for the tool that should be called by the agent
For 'tool_call' type tests: Whether to check if any tool matches the expected call pattern
Metadata from a previous conversation to use as context for this test
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_UPDATE_CONVAI_KNOWLEDGE_BASETool to update the name of a knowledge base document in ElevenLabs Conversational AI. Use when you need to rename an existing knowledge base document.
Input parameters
A custom, human-readable name for the document.
The id of a document from the knowledge base. This is returned on document addition.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_UPDATE_CONVAI_SECRETTool to update an existing secret in the ElevenLabs ConvAI workspace. Use when you need to modify the name or value of an existing API key, token, or other sensitive value stored in the workspace.
Input parameters
Updated name identifier for the secret. Must be unique within the workspace.
Type of operation. Must be the literal value 'update' for updating secrets.
The updated secret value to store securely in the workspace.
The unique identifier of the workspace secret to update. This ID is returned when creating or listing secrets.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_UPDATE_CONVAI_SETTINGSTool to update Convai settings for the workspace. Use when you need to modify webhook configurations, RAG retention settings, MCP server capabilities, or Livekit stack preferences.
Input parameters
Webhook configuration for ConvAI conversations.
Whether the workspace can use MCP servers
Valid Livekit stack types for the default_livekit_stack setting.
Number of days to retain RAG data. Maximum: 30 days
Webhook configuration for conversation initiation client data.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_UPDATE_CONVAI_SETTINGS_DASHBOARDTool to update Convai dashboard settings for the workspace. Use when you need to configure dashboard charts for monitoring conversational AI performance.
Input parameters
List of dashboard charts (max 4), each representing call success metrics, criteria evaluations, or data collection insights
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_UPDATE_CONVAI_TOOLTool to update an existing conversational AI tool in ElevenLabs workspace. Use when modifying tool settings, descriptions, API endpoints, or behavior configurations. Requires the complete tool_config object with all required fields for the tool type.
Input parameters
ID of the tool to update.
Complete tool configuration object to update. Must include 'type' field (webhook/client/system/mcp) and all type-specific required fields. For webhook: requires name, description, api_schema. For client: requires name, description. For system: requires name, params. For mcp: requires name, description, integration_type, mcp_tool_name, mcp_tool_description, mcp_server_id, mcp_server_name. Optional fields include: assignments, disable_interruptions, dynamic_variables, execution_mode, force_pre_tool_speech, response_timeout_secs, tool_call_sound, tool_call_sound_behavior, tool_error_handling_mode.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_UPDATE_PRONUNCIATION_DICTIONARIESUpdates a project's pronunciation dictionaries on ElevenLabs to improve text-to-speech accuracy for specialized terms; note that while multiple dictionaries can be applied, the UI only displays the first.
Input parameters
The ID of the project to which the pronunciation dictionaries will be applied.
List of locators, each provided as a JSON string detailing `pronunciation_dictionary_id` and `version_id`, due to form-data requirements. The ElevenLabs UI currently displays only the first applied dictionary.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_UPDATE_PRONUNCIATION_DICTIONARYPartially updates a pronunciation dictionary's metadata (name or archived status) without changing its version. Use when you need to rename or archive/unarchive a dictionary.
Input parameters
The name of the pronunciation dictionary, used for identification only.
Whether to archive the pronunciation dictionary.
The unique identifier of the pronunciation dictionary to update.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_UPDATE_WORKSPACE_WEBHOOKTool to update a specified workspace webhook by its ID. Use when you need to modify webhook settings such as the display name or enable/disable status.
Input parameters
The display name of the webhook (used for display purposes only).
The unique ID for the webhook
Whether to disable or enable the webhook
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ELEVENLABS_VOICE_GENERATION_PARAMETERSFetches configurable parameters for ElevenLabs voice generation, used to determine available settings (e.g., accents, character limits) prior to audio synthesis; returns metadata only, not audio.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 33 agents privately built on Nagent that already use ElevenLabs.
Build on Nagent
Connect ElevenLabs to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find ElevenLabs, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, ElevenLabs is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once ElevenLabs is connected, you configure its 155 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop ElevenLabs steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a ElevenLabs event fires, the agent kicks off automatically.
Every ElevenLabs action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While ElevenLabs ships with 155 pre-built artificial intelligence actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching ElevenLabs together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build ElevenLabs-based workflows tailored to your business.