Rev.ai MCP by usefulapi

Last 30 days

Uptime

100%

Response time

266 ms typical, 266 ms slowest 5%

Last check

2 h ago

Next check

in 5 h

How to call it

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "rev-ai-mcp-by-usefulapi": {
      "type": "http",
      "url": "https://rev-ai.usefulapi.io/mcp"
    }
  }
}

8 tools

• revai_get_account

  The Rev.ai account behind the token: email, free, purchased, total and invoiced balance (USD) and whether HIPAA is on. GET /account.

• revai_list_jobs

  List transcription jobs from the last 30 days, newest first: id, status (in_progress, transcribed, failed), name, duration, language, failure reason. Page with starting_after = the previous reply's next_starting_after. GET /jobs.

• revai_get_job

  One transcription job by id: status (in_progress, transcribed, failed), timestamps, duration, language, failure reason. Poll this until status is transcribed. GET /jobs/{id}.

• revai_submit_job

  WRITE: start an asynchronous machine transcription job for an audio or video file at a public URL. It uses Rev.ai credit (free credit first). Returns the job with status in_progress; then poll revai_get_job and read the result with revai_get_transcript. Human transcription is not

• revai_delete_job

  WRITE: permanently delete a finished (transcribed or failed) job with its media and transcript. This cannot be undone. A job still in progress cannot be deleted. DELETE /jobs/{id}.

• revai_get_transcript

  The transcript of a transcribed job. format=text (default) is plain text with speaker labels and timestamps; format=segments is a list of {speaker, start, end, text} per speaker turn (seconds). Long transcripts are paged: repeat with next_offset until it is null. GET /jobs/{id}/t

• revai_get_summary

  The summary of a transcribed job. It exists only if the job was submitted with summarization_type. Paged by character like revai_get_transcript. GET /jobs/{id}/transcript/summary.

• revai_get_captions

  Captions for a transcribed job as SRT (default) or WebVTT. Long files are paged by character: repeat with next_offset until it is null. For multichannel jobs pass speaker_channel. GET /jobs/{id}/captions.

Security scan

• No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks