Affordable, accurate, easy-to-use speech-to-text solutions powered by people and A.I working together. Rev offers transcripts, captions, subtitles, and more.
Affordable, accurate, easy-to-use speech-to-text solutions powered by people and A.I working together. Rev offers transcripts, captions, subtitles, and more. On Nagent, Rev AI is exposed as a fully-configurable transcription integration that any agent can call — 36 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 transcription 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_CREATE_RTMP_STREAMTool to create an RTMP live stream session for real-time transcription of live audio/video streams. Use when you need to set up streaming transcription via RTMP protocol.
Input parameters
Language code for transcription in ISO 639-1 format (e.g., 'en', 'es', 'fr').
Custom metadata string to associate with the stream for tracking purposes.
Processing priority setting (e.g., 'accuracy', 'speed').
Transcriber type to use for processing (e.g., 'machine').
Whether to filter profanity from the transcription output.
Whether to enable detailed partial transcription results during streaming.
Whether to remove disfluencies (e.g., 'um', 'uh') from the transcription.
Whether to skip post-processing phase of transcription.
ID of a custom vocabulary to improve transcription accuracy for domain-specific terms.
Whether to enable speaker switching detection in the stream.
Maximum duration in seconds for 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_DELETE_ALIGNMENT_JOBTool to delete a forced alignment job and its associated data. Use when you need to permanently remove an alignment job after confirming it's no longer needed.
Input parameters
The unique identifier of the forced alignment 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_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_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_DELETE_LANGUAGE_ID_JOBTool to delete a language identification job and its associated data. Use when you need to permanently remove a language ID job that is no longer needed.
Input parameters
The unique identifier of the language identification 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_DELETE_SENTIMENT_JOBTool to delete a specific sentiment analysis job and its associated data. Use when you need to permanently remove a sentiment analysis job after confirming it's no longer needed.
Input parameters
The unique identifier of the sentiment analysis 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_DELETE_TOPIC_EXTRACTION_JOBTool to delete a topic extraction job and its associated data. Use when you need to permanently remove a topic extraction job after confirming it's no longer needed.
Input parameters
The unique identifier of the topic extraction 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_GET_ACCOUNTRetrieves Rev AI account information including email, credit balance (in hours), and HIPAA status. Returns current free, purchased, and total balance available for transcription services. No parameters required - uses authenticated credentials.
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_GET_ALIGNMENT_JOBTool to get details of a specific forced alignment job including its status. Use when checking the progress of alignment job processing.
Input parameters
Unique identifier of the forced alignment 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_GET_ALIGNMENT_TRANSCRIPTTool to retrieve the aligned transcript with timestamps for a completed alignment job. Use after confirming the alignment job status is 'completed'.
Input parameters
Unique identifier of the alignment job to retrieve the transcript 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
REV_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_GET_CAPTIONS_TRANSLATIONTool to retrieve translated captions for a completed Rev.ai transcription job. Use after confirming the job has translation enabled and is complete.
Input parameters
The ID of the completed transcription job that was submitted with translation enabled.
Caption format: SRT (application/x-subrip) or WebVTT (text/vtt).
The target language code for translation (e.g., 'es' for Spanish, 'fr' for French, 'de' for German). Must match one of the target languages specified in translation_config when the job was submitted.
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_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_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_GET_LANGUAGE_ID_JOBTool to fetch details of a language identification job by its ID. Use when checking job status and retrieving language identification results.
Input parameters
Unique identifier of the language identification 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_GET_LANGUAGE_ID_RESULTTool to retrieve language identification results for a completed job. Use when you need to get detected language and confidence scores for an audio file.
Input parameters
Unique identifier of the language identification job.
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_GET_LIST_OF_JOBSRetrieves a list of transcription jobs from the past 30 days in reverse chronological order (newest first). Use this tool to: - View recent transcription jobs and their statuses - Monitor job progress (in_progress, transcribed, failed) - Check job details like duration, language, and submission options - Paginate through large result sets using cursor-based pagination - Find specific jobs for further operations (get transcript, get captions, delete) Note: Jobs older than 30 days are not returned. Supports pagination up to 1000 jobs per request.
Input parameters
Maximum number of jobs to return per call. Defaults to 100 if not specified. Maximum allowed is 1000.
Job ID for cursor-based pagination. Returns jobs created chronologically before (but not including) this job ID. Use to paginate backwards through results.
Job ID for cursor-based pagination. Returns jobs created chronologically after (but not including) this job ID. Use the last job ID 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
REV_GET_SENTIMENT_JOBTool to fetch details of a sentiment analysis job by its ID. Use when checking sentiment analysis job status and metadata.
Input parameters
Unique identifier of the sentiment analysis 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_GET_SENTIMENT_RESULTTool to retrieve sentiment analysis results for a completed Rev.ai sentiment job. Use when you need to get sentiment scores and labels for transcribed content. The job must be in 'completed' status before results can be retrieved.
Input parameters
Unique identifier of the sentiment analysis job. The job must be in 'completed' status to retrieve results.
Filter sentiment results by sentiment type.
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_GET_TOPIC_EXTRACTION_RESULTTool to retrieve topic extraction results for a completed job. Use after confirming the topic extraction job is complete. Returns identified topics with relevance scores and supporting evidence from the content.
Input parameters
Unique identifier of the topic extraction job to retrieve results for.
Optional threshold value to filter topics by score. Only topics with scores above this threshold will be returned.
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_GET_TOPIC_JOBTool to fetch details of a topic extraction job by its ID. Use when you need to check the status of a topic extraction job or retrieve its metadata.
Input parameters
Unique identifier of the topic extraction 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_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_GET_TRANSCRIPT_SUMMARYTool to retrieve a summary of the transcript for a completed transcription job. Use after confirming the job is complete and was submitted with summarization_config enabled.
Input parameters
Identifier for the completed transcription job.
Output format. Supported values: text/plain (default) for plain text summary, or application/vnd.rev.transcript.v1.0+json for JSON format with 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
REV_GET_TRANSCRIPT_TRANSLATIONTool to retrieve a translated version of the transcript for a completed Rev.ai job. Use after confirming job is complete and translation was requested when submitting the job.
Input parameters
The ID of 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.
The target language code for translation (e.g., 'es' for Spanish, 'fr' for French, 'de' for German).
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_LIST_ALIGNMENT_JOBSTool to retrieve a list of all forced alignment jobs for the account. Use when you need to view and monitor forced alignment job statuses, check job details, or paginate through alignment job results.
Input parameters
Maximum number of alignment jobs to return per call. Defaults to 100.
Job ID for cursor-based pagination. Returns jobs created chronologically after (but not including) this job ID. Use the last job ID 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
REV_LIST_CUSTOM_VOCABULARIESTool to retrieve a list of all custom vocabularies for the account. Use when needing to view available custom vocabularies that can be used to improve transcription accuracy on domain-specific terminology.
Input parameters
Maximum number of custom vocabularies to return. Defaults to 100 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
REV_LIST_LANGUAGE_ID_JOBSTool to retrieve a list of language identification jobs for the account. Use when you need to check the status of language identification jobs or monitor their progress.
Input parameters
Maximum number of jobs to return per call. Defaults to 100.
Job ID for cursor-based pagination. Returns jobs created chronologically after (but not including) this job ID. Use the last job ID 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
REV_LIST_SENTIMENT_JOBSTool to retrieve a list of all sentiment analysis jobs for the account. Use when you need to view sentiment analysis job history, monitor job statuses, or find specific jobs for further operations.
Input parameters
Maximum number of jobs to return per call. Defaults to 100 if not specified. Maximum allowed is 1000.
Job ID for cursor-based pagination. Returns jobs created chronologically after (but not including) this job ID. Use the last job ID 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
REV_LIST_TOPIC_JOBSTool to retrieve a list of all topic extraction jobs for the account. Use when you need to view topic extraction job history, monitor job statuses, or find specific jobs for further operations.
Input parameters
Maximum number of jobs to return per call. Defaults to 100 if not specified. Maximum allowed is 1000.
Job ID for cursor-based pagination. Returns jobs created chronologically after (but not including) this job ID. Use the last job ID 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
REV_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_SUBMIT_ALIGNMENT_JOBTool to submit an audio file with existing transcript for forced alignment. Use when you need to add accurate timestamps to transcript text by aligning it with the corresponding audio file. Forced alignment is useful when you already have a transcript but need precise word-level or phrase-level timestamps. Both the audio file and transcript must be publicly accessible via HTTP(S) URLs.
Input parameters
Language of the audio and transcript. Must be one of: en (English), es (Spanish), fr (French). Default is English (en)
Custom metadata string (up to 512 chars) stored with the alignment job. Useful for tracking job context, order IDs, user IDs, etc.
Configuration specifying the audio file URL to be aligned
Optional webhook configuration for job completion notifications.
Automatically delete the completed alignment job and its data after this many seconds. Useful for managing storage and privacy. Set to 0 to delete immediately after completion
Configuration specifying the transcript text file URL to be aligned with the 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
REV_SUBMIT_CUSTOM_VOCABULARYSubmits a custom vocabulary to Rev.ai for improved speech recognition accuracy on domain-specific terms. The vocabulary is processed asynchronously and returns immediately with an 'in_progress' status. Use the returned vocabulary ID in transcription jobs to boost recognition of your custom phrases. Common use cases: brand names, technical jargon, medical terms, product names, industry acronyms. Rate limit: 150 requests per 2 minutes.
Input parameters
List of phrases or words to boost in speech recognition. Each phrase must: contain only ASCII letters and punctuation (U+0000-U+007F, no numbers or accented characters), have at least one letter, and be 34 characters or less per word. Best practice: use 500 or fewer short phrases (5 words or less each) for optimal accuracy. API limit: 6000 phrases for English, 1000 for other languages.
Optional user-defined metadata string to store additional context about the vocabulary (e.g., domain, version, purpose). This is returned with the vocabulary details for reference.
Optional client-provided identifier for the custom vocabulary. If not provided, Rev.ai will auto-generate an ID. Use this to track vocabularies in your system.
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_SUBMIT_LANGUAGE_ID_JOBTool to submit an audio file for language identification to detect the spoken language. Use when you need to identify which language is spoken in an audio recording.
Input parameters
Custom metadata string (up to 512 chars) stored with the job and returned in responses. Useful for tracking job context, order IDs, user IDs, etc.
Configuration specifying the audio source URL to analyze
Configuration for webhook notifications when the job completes.
Automatically delete the completed job and its data after this many seconds. Useful for managing storage and privacy. Set to 0 to delete immediately after completion
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_SUBMIT_SENTIMENT_ANALYSIS_JOBSubmit text for sentiment analysis to detect positive, negative, or neutral sentiments. Use when analyzing customer feedback, reviews, support tickets, or transcribed audio for emotional tone. Provide either plain text (text parameter) or a Rev AI transcript JSON (transcript_json parameter). The job processes asynchronously; use the returned job ID to retrieve results when complete.
Input parameters
Plain text content to analyze for sentiment. Use this when submitting raw text for analysis
Language code for the text content (e.g., 'en' for English, 'es' for Spanish). Required if using non-English text
Custom metadata string stored with the job and returned in responses. Useful for tracking job context, order IDs, user IDs, etc.
JSON transcript structure from Rev AI speech-to-text API.
Webhook configuration for job completion notifications.
Time in seconds after which the job will be automatically deleted. Useful for managing storage and privacy
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_SUBMIT_TOPIC_EXTRACTION_JOBTool to submit text or transcripts for topic extraction to identify key topics and themes. Use when analyzing conversation content, meeting transcripts, or text to extract main discussion points. Supports both plain text input (up to 14000 words) and structured JSON transcripts from Rev.ai's Speech-to-Text API. Results are processed asynchronously; use the returned job ID to check status and retrieve extracted topics when complete.
Input parameters
JSON transcript format from Rev.ai Speech-to-Text API.
Plain text content to analyze for topic extraction. Maximum 14000 words. Use this for simple text input
Language code for the content (e.g., 'en', 'es', 'fr'). If not specified, language may be auto-detected from the content
Custom metadata string (up to 512 chars) stored with the job and returned in responses. Useful for tracking job context, order IDs, user IDs, etc.
Configuration for webhook notifications when job completes.
Automatically delete the completed job and its data after this many seconds. Useful for managing storage and privacy. Set to 0 to delete immediately after completion
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_SUBMIT_TRANSCRIPTION_JOBSubmit an audio or video file for asynchronous transcription using Rev.ai. Use this action to convert speech to text from media files. Provide either a publicly accessible URL (media_url) or upload file bytes directly. The job processes asynchronously; use the returned job ID to check status and retrieve the transcript when complete. Supports speaker diarization, punctuation, profanity filtering, custom vocabularies, and multiple languages.
Input parameters
Binary audio/video content to upload directly (use when media_url is not available). File size limit: 2GB for direct uploads
Language code for the audio (ISO 639-1 or BCP-47 format, lowercase). Supports English, Spanish, French, German, Portuguese, Italian, and 40+ others. Use 'auto' for automatic detection. Note: filter_profanity and skip_punctuation are only available for English transcription
Custom metadata string (up to 512 chars) stored with the job and returned in responses. Useful for tracking job context, order IDs, user IDs, etc.
Publicly accessible HTTP(S) URL of the audio/video file to transcribe. Supports formats like MP3, MP4, WAV, FLAC, Ogg, and others supported by FFmpeg. File size limit: 5TB via URL
HTTPS URL where Rev.ai will POST a notification when transcription completes. Webhook receives the job object as JSON
Set to true to replace profane words with asterisks in the transcript. Default false returns raw transcription without filtering
Set to true to disable speaker diarization (identifying different speakers). Default false means speakers will be labeled as 'Speaker 1', 'Speaker 2', etc.
Set to true to disable automatic punctuation in the transcript. Default false adds periods, commas, question marks, etc.
Configuration for automatic transcript translation into target languages.
List of custom vocabulary IDs to improve transcription accuracy for domain-specific terms, proper nouns, technical jargon, or brand names. Submit vocabularies separately first
Automatically delete the completed job and its data after this many seconds. Useful for managing storage and privacy. Set to 0 to delete immediately after completion
Advanced settings for controlling transcription behavior and output format.
Number of audio channels to treat as separate speakers (for multi-channel audio files). Each channel will be transcribed separately and attributed to a different speaker. Use when you have recordings with isolated speaker tracks
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 63 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 36 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 36 pre-built transcription 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.