> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Rev AI

> Rev AI provides advanced machine learning and speech recognition services for converting audio and video to text.

![Rev AI logo](https://mintcdn.com/composio-preview/YYC5iurbUCUzEs77/images/toolkits/rev_ai.svg?fit=max\&auto=format\&n=YYC5iurbUCUzEs77\&q=85\&s=4ae39246a2e1f42756917d78d1d68af0)

* **Category:** audio & speech
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 11
* **Triggers:** 0
* **Slug:** `REV_AI`
* **Version:** 20261101\_00

## Tools

> [accordion] Delete Custom Vocabulary
>
> **Slug:** `REV_AI_DELETE_CUSTOM_VOCABULARY`
>
> Tool 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
>
> **id** `string` *required*
>
> Unique identifier of the custom vocabulary to delete
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Job By ID
>
> **Slug:** `REV_AI_DELETE_JOB_BY_ID`
>
> Tool 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
>
> **id** `string` *required*
>
> The unique identifier of the job to delete
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Account
>
> **Slug:** `REV_AI_GET_ACCOUNT`
>
> Tool to retrieve developer account details. Use after authenticating with Rev AI.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Captions
>
> **Slug:** `REV_AI_GET_CAPTIONS`
>
> Tool to retrieve captions (SRT or VTT) for a completed Rev.ai transcription job. Use after confirming the job status is 'completed'.
>
> #### Input Parameters
>
> **accept** `string ("application/x-subrip" | "text/vtt")`
>
> Caption format: SRT (application/x-subrip) or WebVTT (text/vtt).
>
> **job\_id** `string` *required*
>
> The ID of the completed transcription job.
>
> **channel\_id** `integer`
>
> Optional audio channel number for multi-channel jobs.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Custom Vocabulary Details
>
> **Slug:** `REV_AI_GET_CUSTOM_VOCABULARY_DETAILS`
>
> Tool 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
>
> **id** `string` *required*
>
> Unique identifier of the custom vocabulary to retrieve.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Job by ID
>
> **Slug:** `REV_AI_GET_JOB_BY_ID`
>
> Tool to fetch details of a transcription job by its ID. Use when confirming job status and metadata are accurate.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> Unique identifier of the transcription job to retrieve.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get List of Jobs
>
> **Slug:** `REV_AI_GET_LIST_OF_JOBS`
>
> Tool 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
>
> **limit** `integer`
>
> Maximum number of jobs to return (default 100, max 1000)
>
> **ending\_before** `string`
>
> Only return jobs created before the given job ID.
>
> **starting\_after** `string`
>
> Only return jobs created after the given job ID.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Transcript by ID
>
> **Slug:** `REV_AI_GET_TRANSCRIPT_BY_ID`
>
> Tool 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
>
> **id** `string` *required*
>
> Identifier for the transcription job.
>
> **accept** `string ("application/vnd.rev.transcript.v1.0+json" | "text/plain")`
>
> 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** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Start Stream Transcription
>
> **Slug:** `REV_AI_START_STREAM_TRANSCRIPTION`
>
> Constructs a WebSocket URL for a Rev.ai real-time transcription stream. Connect to the returned URL to start streaming.
>
> #### Input Parameters
>
> **language** `string`
>
> Language code in ISO 639-1 format for transcription, default 'en'.
>
> **metadata** `string`
>
> Optional user metadata string to associate with the stream.
>
> **priority** `string ("speed" | "quality")`
>
> Priority of transcription processing: 'speed' or 'quality'.
>
> **start\_ts** `number`
>
> Initial timestamp (in seconds) from which to start transcription.
>
> **transcriber** `string`
>
> Select a transcriber model, if multiple are available.
>
> **content\_type** `string` *required*
>
> Audio MIME type and parameters (e.g., 'audio/x-raw;layout=interleaved;rate=16000;format=S16LE;channels=1', 'audio/x-wav', 'audio/x-flac').
>
> **filter\_profanity** `boolean`
>
> Whether to filter profanity from transcripts.
>
> **detailed\_partials** `boolean`
>
> Whether to send detailed partial results.
>
> **remove\_disfluencies** `boolean`
>
> Whether to remove disfluencies (um, uh) from transcripts.
>
> **skip\_postprocessing** `boolean`
>
> Whether to skip post-processing phase.
>
> **custom\_vocabulary\_id** `string`
>
> ID of a custom vocabulary to apply, if available.
>
> **delete\_after\_seconds** `integer`
>
> If set, server will delete the stream results after given seconds.
>
> **enable\_speaker\_switch** `boolean`
>
> Whether to enable speaker-switch detection.
>
> **max\_connection\_wait\_seconds** `integer`
>
> Maximum seconds to wait for WebSocket connection establishment.
>
> **max\_segment\_duration\_seconds** `integer`
>
> Maximum duration in seconds of each transcription segment.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Submit Custom Vocabulary
>
> **Slug:** `REV_AI_SUBMIT_CUSTOM_VOCABULARY`
>
> Tool to submit a custom vocabulary for improved speech recognition. Use when you want to process domain-specific terms asynchronously.
>
> #### Input Parameters
>
> **phrases** `array` *required*
>
> List of phrases or words to include in the custom vocabulary.
>
> **metadata** `string`
>
> Optional user-defined metadata for the custom vocabulary.
>
> **custom\_vocabulary\_id** `string`
>
> Optional unique identifier for the custom vocabulary.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Submit Transcription Job
>
> **Slug:** `REV_AI_SUBMIT_TRANSCRIPTION_JOB`
>
> Tool to submit a new transcription job. Use when you have a media URL or file bytes ready for async processing.
>
> #### Input Parameters
>
> **file** `string`
>
> Binary audio content to upload if media\_url is not used
>
> **language** `string`
>
> ISO 639-1 or BCP-47 code to override default language
>
> **metadata** `string`
>
> Arbitrary string returned verbatim with job status
>
> **media\_url** `string`
>
> HTTP(S) URL of the media file to transcribe
>
> **callback\_url** `string`
>
> Webhook URL called on job completion
>
> **filter\_profanity** `boolean`
>
> If true, filter profanity from the transcript
>
> **skip\_diarization** `boolean`
>
> If true, do NOT perform speaker diarization
>
> **skip\_punctuation** `boolean`
>
> If true, do NOT auto-punctuate transcript
>
> **custom\_vocabularies** `array`
>
> List of custom vocabularies to apply
>
> **delete\_after\_seconds** `integer`
>
> Automatically delete job this many seconds after completion
>
> **transcription\_config** `object`
>
> Settings for advanced transcription options.
>
> **speaker\_channel\_count** `integer`
>
> Number of audio channels to treat as separate speakers
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
