Convolo.ai is an AI-powered communications platform designed to enhance sales calls and improve conversion rates through rapid lead response and integration capabilities.
Convolo.ai is an AI-powered communications platform designed to enhance sales calls and improve conversion rates through rapid lead response and integration capabilities. On Nagent, Convolo AI is exposed as a fully-configurable ai sales tools integration that any agent can call — 7 actions, and API key authentication. No code is required to wire Convolo AI into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Convolo AI to automate the kinds of tasks ai sales tools 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 Convolo AI 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 Convolo AI, with input parameters and output schema. Drop these into any step of an agent built in Helix.
CONVOLO_AI_CREATE_CHARACTERTool to create a new character. Use when you have name, voice type, backstory, and optional actions ready.
Input parameters
Optional list of actions the character can perform.
Name of the character to create.
Background information or story for the character.
Voice type to assign; see Voice List API for available values.
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
CONVOLO_AI_EVALUATE_CHARACTEREvaluates a conversation session across 9 quality dimensions (clarity, courtesy, product knowledge, etc.) using AI analysis. Returns structured ratings and feedback. Prerequisites: - A valid session_id from Get Character Response - A character_id from Create Character - Prompt must include \[\[conversation_history\]\] placeholder Note: This API requires Professional Plan or higher access.
Input parameters
Evaluation instructions that MUST include the placeholder \[\[conversation_history\]\]. The conversation history will be automatically fetched and inserted. You can add other placeholders and provide their values via the 'variables' parameter.
Optional key-value pairs for custom variables referenced in your prompt (e.g., \[\[customer_name\]\], \[\[product\]\]). Do NOT include \[\[conversation_history\]\] here—it's automatically provided.
The ID of the conversation session to evaluate. Obtain this from a Get Character Response action.
The ID of the character that will perform the evaluation. Obtain this from a Create Character action.
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
CONVOLO_AI_GENERATE_STARTER_CONVERSATIONGenerates AI-powered conversation starter suggestions for a character. This tool creates contextually relevant opening lines or follow-up dialogue suggestions that can be used to initiate or continue conversations with AI characters. Perfect for chatbots, virtual assistants, game NPCs, or interactive storytelling applications. Use this when you need: - Opening conversation starters for a new interaction (sessionId="-1") - Follow-up suggestions based on an ongoing conversation (provide existing sessionId) - Multiple conversation options to choose from
Input parameters
The unique identifier of the character for which to generate conversation starters. Obtain this from the Create Character action.
The session identifier for context-aware suggestions. Use "-1" to generate opening conversation starters for a new session, or provide an existing session ID for follow-up dialogue suggestions.
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
CONVOLO_AI_GET_CHARACTER_RESPONSETool to generate a response from a ConvAI character based on text or audio input. Use when needing a text or voice reply in an ongoing session.
Input parameters
Mono WAV audio file bytes; provide only if not sending userText
ID of the character to interact with
Enable SSE streaming; "True" or "False"
User text input; provide only if not sending audio
Session identifier; use "-1" to start a new session
Sample rate of the uploaded audio in Hz
Whether to return response 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
CONVOLO_AI_LIST_VOICESTool to retrieve the list of available voice types. Use when selecting voices before generating speech.
Input parameters
Override the Accept header if provided.
Override the Content-Type header if provided.
If true, use https://api.convai.com as base URL instead of default.
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
CONVOLO_AI_SET_CORE_AI_SETTINGSUpdates the core AI settings (model and/or temperature) for an existing Convai character. Use this action to: - Switch the AI model powering a character (e.g., from GPT-4o to Claude) - Adjust response creativity via temperature parameter (0.0=deterministic, 1.0=creative) - Fine-tune character behavior without recreating the character Prerequisites: Requires a valid charID from a previously created character. At least one of model_group_name or temperature must be specified.
Input parameters
The unique identifier (charID) of the character to update. Obtain this from CREATE_CHARACTER or character listing endpoints.
Controls response randomness/creativity (0.0-1.0). Lower values (0.0-0.3) make responses more focused and deterministic; higher values (0.7-1.0) increase creativity and variation. Default behavior maintained if not specified. Optional - provide only when adjusting.
AI language model to use for this character. Choose based on desired capabilities: GPT models for general use, Claude for nuanced conversations, Gemini for multimodal, Llama for open-source. Optional - provide only when changing the 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
CONVOLO_AI_UPLOAD_KNOWLEDGE_BANKTool to upload a knowledge bank file. Use when you have a file ready to add to Convolo AI's knowledge bank (Enterprise plan only).
Input parameters
Raw bytes of the knowledge bank file to upload
Name of the file being uploaded
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 57 agents privately built on Nagent that already use Convolo AI.
Build on Nagent
Connect Convolo AI 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 Convolo AI, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Convolo AI is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Convolo AI is connected, you configure its 7 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Convolo AI 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 Convolo AI event fires, the agent kicks off automatically.
Every Convolo AI 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 Convolo AI ships with 7 pre-built ai sales tools actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Convolo AI together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Convolo AI-based workflows tailored to your business.