otherapi_key

Rev AI

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

Verdict

Rev AI transcribes audio and video files through Switchy, giving your team instant access to speech-to-text without leaving the workspace. @mention it to submit recordings for transcription, check job status, retrieve finished transcripts in multiple formats (JSON, plain text, SRT, VTT), or pull captions for video projects. Useful for content teams processing interviews, support teams reviewing call recordings, or anyone who needs searchable text from audio. You'll need a Rev AI API key with transcription permissions. Jobs process asynchronously — expect a few minutes per file depending on length.

Common use cases

  • Transcribe customer call recordings for analysis
  • Generate captions for training videos
  • Convert podcast episodes to searchable text
  • Pull transcripts from recorded interviews
  • Review meeting audio without replaying

Integration

Vendor
Rev AI
Category
other
Auth
API_KEY
Tools
11
Composio slug
rev_ai

Tools

  • Delete Custom Vocabulary
    destructive

    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.

  • Delete Job By ID
    destructive

    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.

  • Get Account

    Tool to retrieve developer account details. use after authenticating with 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'.

  • 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.

  • Get Job by ID

    Tool to fetch details of a transcription job by its id. use when confirming job status and metadata are accurate.

  • 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.

  • Get Transcript by ID

    Tool to retrieve the transcript of a completed rev.ai job. use after confirming job is complete. supports json, plaintext, vtt or srt formats.

  • Start Stream Transcription

    Tool to start a websocket transcription stream. use when you need real-time speech-to-text streaming via 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.

  • Submit Transcription Job

    Tool to submit a new transcription job. use when you have a media url or file bytes ready for async processing.

Setup

Setup guide

  1. 11. Open your Switchy workspace settings and navigate to the Integrations tab. 2. Search for Rev AI and click Connect. 3. You'll be prompted to paste your Rev AI API key — generate one from your Rev AI developer dashboard under API Keys. 4. Grant the key transcription permissions (read and write access to jobs, vocabularies, and account details). 5. Paste the key into Switchy and click Authorize. 6. Switchy confirms the connection by fetching your account details. 7. Open any Space and type '@Rev AI get list of jobs' to verify the integration works — you should see recent transcription jobs or an empty list if you haven't submitted any yet. 8. To test a full workflow, upload an audio file to your Space, then prompt '@Rev AI submit this file for transcription' and check back in a few minutes for the completed transcript.

What teammates see: by default, memories from Rev AI are scoped to the Space (PROJECT visibility) - you can mark any memory PRIVATE or share it ORG-wide.

Works well with

Top models

Compatibility data appears once enough Spaces have used this MCP together with a given model.

How Switchy teams use it

Not enough Spaces yet to publish anonymised usage stats (we require ≥ 50 Spaces per week).

Starter prompts

Transcribe Uploaded Audio

@Rev AI transcribe the audio file I just uploaded and return the plain text transcript when it's ready
Open in a Space →

Check Recent Jobs

@Rev AI show me all transcription jobs from the last two weeks with their current status
Open in a Space →

Get SRT Captions

@Rev AI fetch the SRT captions for job ID [paste ID here] so I can add them to the video
Open in a Space →

Retrieve Specific Transcript

@Rev AI get the JSON transcript for job [paste ID here] and summarize the key points discussed
Open in a Space →

Review Account Usage

@Rev AI pull my account details and let me know how many transcription minutes I have left this month
Open in a Space →

Example outputs

Illustrative - representative of the model's voice and quality, not literal recordings.

Prompt

@revai list all transcription jobs from the last week and show me which ones are still processing

Output

Found 12 transcription jobs from the past 7 days. 9 are completed, 2 are in_progress, and 1 failed. The in-progress jobs are: 'team-standup-2024-01-15.mp3' (started 8 minutes ago, 45% complete) and 'client-call-recording.wav' (started 23 minutes ago, 78% complete). The failed job 'podcast-episode-draft.m4a' encountered an unsupported audio format error. All completed jobs are available for transcript retrieval.

Notes

This example shows the MCP's ability to query job history and surface status at a glance. Rev AI retains job metadata for 30 days, so older transcriptions won't appear. Requires valid API key with read access to your account's job queue.

Prompt

@revai get the full transcript for job ID Umx5c6F7pH44 in plain text format and save it to our meeting notes

Output

Retrieved transcript for job Umx5c6F7pH44 (duration: 42 minutes, completed 3 hours ago). The transcript contains 8,347 words with speaker labels and timestamps. Extracted plain text format as requested. Key discussion points include Q1 roadmap priorities, API rate limit adjustments, and the new customer onboarding flow. Transcript saved to your Space for reference and further analysis.

Notes

This demonstrates fetching completed transcripts in a specific format (plaintext, JSON, SRT, or VTT). The job must be in 'completed' status—attempting to retrieve a transcript for an in-progress or failed job will return an error. Speaker labels depend on your Rev AI plan tier.

Prompt

@revai review all completed transcription jobs from this month and summarize the main topics discussed across our team meetings

Output

Analyzed 18 completed transcription jobs from January 2024 (total duration: 9.2 hours). Recurring themes: product launch timeline mentioned in 12 meetings, customer feedback discussed in 8, hiring pipeline in 6, and infrastructure scaling in 5. The most frequent action items were 'finalize pricing model' (appeared 7 times) and 'schedule design review' (appeared 5 times). Three meetings flagged budget concerns; two celebrated milestone completions.

Notes

This example pairs Rev AI's transcript retrieval with the AI's reasoning to synthesize patterns across multiple jobs. The MCP fetches raw transcripts; the AI performs the thematic analysis. Useful for retrospectives, but note that Rev AI's 30-day job retention means older meetings won't be included in the summary.

Use-case deep-dives

Customer interview transcription for product teams

When Rev AI beats manual notes for weekly user calls

A 5-person product team runs 8-12 customer interviews per sprint. They need transcripts searchable across quarters, not just raw audio files in Drive. Rev AI's MCP wins here because the Get List of Jobs tool lets anyone pull the last 30 days of transcripts into a shared context without asking who recorded what. The Get Transcript by ID tool returns JSON, so you can pipe interview quotes directly into feature specs or roadmap docs. The threshold: if your team does fewer than 3 interviews a month, the API key overhead isn't worth it—just use meeting recorder apps with built-in transcription. But at 2+ calls per week, Rev AI keeps the entire interview corpus accessible in Switchy without manual copy-paste. Set it up once, query transcripts forever.

Podcast post-production for small media teams

Rev AI for caption workflows when turnaround matters

A 3-person podcast team publishes twice weekly and needs SRT captions for YouTube within 4 hours of recording. Rev AI's Get Captions tool pulls formatted SRT or VTT files the moment transcription completes, so the editor doesn't wait on a third-party dashboard. The Custom Vocabulary tools let you pre-load guest names and niche terms so the transcript doesn't mangle "Kubernetes" into "communities." The trade-off: if your episodes are under 15 minutes and you publish monthly, free-tier tools like Whisper are fine. But at 45-minute episodes twice a week, Rev AI's job queue (visible via Get List of Jobs) keeps production moving without manual file juggling. You'll spend the API cost back in editor hours saved.

Legal deposition review for compliance teams

When Rev AI's delete tools matter for sensitive audio

A 2-person compliance team reviews 6-10 recorded depositions per month and must purge transcripts after 90 days per data retention policy. Rev AI's Delete Job By ID tool lets you script permanent removal from the vendor's servers, not just your local files—critical when audio contains PII or privileged statements. The Get Job by ID tool confirms deletion succeeded before you log the audit trail. The boundary: if your retention window is "forever" or you're handling fewer than 3 depositions quarterly, simpler transcription tools without API complexity are enough. But when you're juggling active cases and mandatory purges, Rev AI's programmatic delete (plus the Get Account tool to verify API limits) keeps you compliant without spreadsheet tracking. Worth the API key if deletion audits are non-negotiable.

Frequently asked

What does the Rev AI MCP do in Switchy?

It lets your team transcribe audio and video files through Rev AI's speech-to-text API without leaving Switchy. You can submit jobs, check their status, retrieve completed transcripts in JSON or plaintext, and download captions in SRT or VTT format. It also manages custom vocabularies to improve accuracy for domain-specific terms.

Do I need a Rev AI account to use this MCP?

Yes. You need an active Rev AI developer account and an API key. Paste the key into Switchy's connection flow and you're done—no OAuth redirect, no admin approval. Transcription costs come from your Rev AI balance, not your Switchy plan.

Can the MCP transcribe live calls or streaming audio?

No. Rev AI's MCP submits pre-recorded files for asynchronous transcription. If you need real-time streaming, you'll have to use Rev AI's streaming API directly—this integration only handles batch jobs that return results after processing completes.

How does this compare to uploading files to Rev AI's web dashboard?

The MCP skips the manual upload step and keeps transcripts inside your Switchy workspace where the whole team can reference them. You lose Rev AI's web editor for fixing mistakes, but you gain programmatic access to job metadata, captions, and custom vocabularies without context-switching.

Who on my team should connect the Rev AI MCP?

Whoever owns your Rev AI account and has the API key. Once connected, any Switchy user in your workspace can submit transcription jobs and retrieve results. Just make sure your Rev AI balance covers the team's usage—Switchy doesn't meter or throttle the calls.

Data last verified 607 hours ago.Sources aggregated hourly to weekly. See docs/architecture/model-directory.md.