Rev AI provides advanced machine learning and speech recognition services for converting audio and video to text.
Rev AI provides advanced machine learning and speech recognition services for converting audio and video to text. On Nagent, Rev AI is exposed as a fully-configurable artificial intelligence integration that any agent can call — 11 actions, and API key authentication. No code is required to wire Rev AI into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Rev AI 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 Rev 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 Rev AI, with input parameters and output schema. Drop these into any step of an agent built in Helix.
REV_AI_DELETE_CUSTOM_VOCABULARYTool to delete a completed custom vocabulary and its data. Use when you need to remove an unused vocabulary after confirming it's no longer needed.
Input parameters
Unique identifier of the custom vocabulary 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
REV_AI_DELETE_JOB_BY_IDTool to delete a completed transcription job and its data. Use when you need to permanently remove a finished job after confirming it's no longer needed.
Input parameters
The unique identifier of the job 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
REV_AI_GET_ACCOUNTTool to retrieve developer account details. Use after authenticating with Rev AI.
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
REV_AI_GET_CAPTIONSTool to retrieve captions (SRT or VTT) for a completed Rev.ai transcription job. Use after confirming the job status is 'completed'.
Input parameters
Caption format: SRT (application/x-subrip) or WebVTT (text/vtt).
The ID of the completed transcription job.
Optional audio channel number for multi-channel jobs.
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
REV_AI_GET_CUSTOM_VOCABULARY_DETAILSTool to retrieve custom vocabulary processing details. Use when needing to fetch the status and submitted phrases for a specific custom vocabulary after creation.
Input parameters
Unique identifier of the custom vocabulary 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
REV_AI_GET_JOB_BY_IDTool to fetch details of a transcription job by its ID. Use when confirming job status and metadata are accurate.
Input parameters
Unique identifier of the transcription job 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
REV_AI_GET_LIST_OF_JOBSTool to get list of transcription jobs from the past 30 days. Use when you need to retrieve and paginate through recent transcription tasks.
Input parameters
Maximum number of jobs to return (default 100, max 1000)
Only return jobs created before the given job ID.
Only return jobs created after the given job 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
REV_AI_GET_TRANSCRIPT_BY_IDTool to retrieve the transcript of a completed Rev.ai job. Use after confirming job is complete. Supports JSON format (with timestamps and speaker info) or plain text format.
Input parameters
Identifier for the transcription job.
Output format. Supported values: application/vnd.rev.transcript.v1.0+json (default) for JSON with timestamps and speaker info, or text/plain for plain text.
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
REV_AI_START_STREAM_TRANSCRIPTIONTool to start a WebSocket transcription stream. Use when you need real-time speech-to-text streaming via Rev.ai.
Input parameters
Language code in ISO 639-1 format for transcription, default 'en'.
Optional user metadata string to associate with the stream.
Priority of transcription processing: 'speed' or 'quality'.
Initial timestamp (in seconds) from which to start transcription.
Select a transcriber model, if multiple are available.
Audio MIME type and parameters (e.g., 'audio/x-raw;layout=interleaved;rate=16000;format=S16LE;channels=1', 'audio/x-wav', 'audio/x-flac').
Whether to filter profanity from transcripts.
Whether to send detailed partial results.
Whether to remove disfluencies (um, uh) from transcripts.
Whether to skip post-processing phase.
ID of a custom vocabulary to apply, if available.
If set, server will delete the stream results after given seconds.
Whether to enable speaker-switch detection.
Maximum seconds to wait for WebSocket connection establishment.
Maximum duration in seconds of each transcription segment.
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
REV_AI_SUBMIT_CUSTOM_VOCABULARYTool to submit a custom vocabulary for improved speech recognition. Use when you want to process domain-specific terms asynchronously.
Input parameters
List of phrases or words to include in the custom vocabulary.
Optional user-defined metadata for the custom vocabulary.
Optional unique identifier for the custom vocabulary.
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
REV_AI_SUBMIT_TRANSCRIPTION_JOBTool to submit a new transcription job. Use when you have a media URL or file bytes ready for async processing.
Input parameters
Binary audio content to upload if media_url is not used
ISO 639-1 or BCP-47 code to override default language
Arbitrary string returned verbatim with job status
HTTP(S) URL of the media file to transcribe
Webhook URL called on job completion
If true, filter profanity from the transcript
If true, do NOT perform speaker diarization
If true, do NOT auto-punctuate transcript
List of custom vocabularies to apply
Automatically delete job this many seconds after completion
Settings for advanced transcription options.
Number of audio channels to treat as separate speakers
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 36 agents privately built on Nagent that already use Rev AI.
Build on Nagent
Connect Rev 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 Rev AI, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Rev AI is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Rev AI is connected, you configure its 11 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Rev 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 Rev AI event fires, the agent kicks off automatically.
Every Rev 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 Rev AI ships with 11 pre-built artificial intelligence actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Rev AI together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Rev AI-based workflows tailored to your business.