Turns recordings and live audio into transcripts with speaker labels, produces SRT and VTT subtitles, and clears finished jobs on request.
11actions available
Every action runs live through MCP. Nothing to build, nothing to maintain.
Ayro submits audio or video files to Rev.ai for high-accuracy transcription. The transcript arrives within hours and can be immediately shared with the customer.
Ayro retrieves the completed transcript of a Rev.ai job. The customer receives the full text, ready to search, analyze, or download.
Ayro checks the status of a transcription job to report progress to the customer. The customer knows whether their transcript is queued, processing, or ready.
Each card is one request a support team gets, and the Rev.ai actions Ayro runs to close it.
Ayro submits a media URL or file bytes for asynchronous processing, waits for the job to report completed, and returns the transcript as JSON with speaker information or as plain text.
Ayro returns SRT or VTT captions for a completed job, so a video going out with subtitles does not wait on someone exporting them by hand from the Rev.ai dashboard.
Ayro opens a WebSocket transcription stream for real-time speech-to-text and reports the developer account behind it, so a live session produces text without waiting for a recording.
Ayro reviews the jobs from the past 30 days, permanently deletes a completed job and its data, and removes a custom vocabulary that has outlived the project it was built for.
How it works
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Ayro reads the Rev.ai actions it has and picks the ones a request needs.
Authorize the Rev.ai account your team already uses — one consent screen, no API keys, no mapping tables. Ayro can only do what you granted that account, and you can disconnect it at any time.
Describe the job the way you would hand it to a teammate. Ayro maps it to the Rev.ai actions that close it and chains as many as the request needs.
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started freeRev.ai · Ayro
What can you do in Rev.ai without me setting anything up?
These, right away:
Great, let's start with the first one.
FAQ
Setup, permissions, and the limits of what Ayro can do inside Rev.ai.
Yes. Delete Job By ID permanently removes a completed transcription job and its data, and Delete Custom Vocabulary does the same for a finished vocabulary. Both are irreversible, so Ayro confirms the job against Get List of Jobs and reads its details back before calling either.
All 11 actions your agent can call on Rev.ai, straight from the live MCP connection.
Delete a completed custom vocabulary and its data.
Delete a completed transcription job and its data.
Retrieve developer account details.
Retrieve captions (SRT or VTT) for a completed Rev.ai transcription job.
Retrieve custom vocabulary processing details.
Fetch details of a transcription job by its ID.
Get list of transcription jobs from the past 30 days.
Retrieve the transcript of a completed Rev.ai job.
Start a WebSocket transcription stream.
Submit a custom vocabulary for improved speech recognition.
Submit a new transcription job.
Same connection, same setup. Pick the next one your team already uses.
Sends approved WhatsApp templates, reads campaign and contact analytics, maintains contacts and tags, and reacts to Shopify cart and order events.
Reports voices and character usage, builds conversational agents with indexed knowledge bases, tunes pronunciation, and queues outbound batch calls.
Reads text out of customer attachments, translates and voices replies, and screens submitted text and images before they reach the queue.
Route a request to a self-hosted model, reuse OpenAI-format endpoints against it, and report which models the host currently has installed.
Finds papers by title, topic, or text snippet, traces citations and references, and profiles authors with their publication metrics.
Scores a submitted passage for AI authorship, checks it for plagiarism against online sources, and measures how closely two texts match.

Authorize the account and your agent has all 11 actions from the first conversation.
