Rev.ai MCP by usefulapi

Working · 639 ms

io.usefulapi/rev-aiv1.8.0 Domain verified

Transcribe audio with Rev.ai: submit jobs by URL, read transcripts, summaries and captions.

Design & Creative

Source Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://rev-ai.usefulapi.io/mcp

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

revai_delete_job Destructive

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}.

job_idstring, required

Rev.ai job id (the `id` from revai_submit_job or revai_list_jobs).

The server marks this tool as destructive. Running it may delete or overwrite data on the server or in any account you connected with your headers.

I understand, run it anyway

Tools (8)

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}.

destructive

Argument	Type	Description
job_id*	string	Rev.ai job id (the `id` from revai_submit_job or revai_list_jobs).

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "job_id"
  ],
  "properties": {
    "job_id": {
      "type": "string",
      "maxLength": 100,
      "minLength": 1,
      "description": "Rev.ai job id (the `id` from revai_submit_job or revai_list_jobs)."
    }
  }
}

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.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {}
}

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.

read-only

Argument	Type	Description
format	string	srt (default) or vtt.
job_id*	string	Rev.ai job id (the `id` from revai_submit_job or revai_list_jobs).
offset	integer	Start position from the previous reply's next_offset (default 0).
max_chars	integer	Most characters to return in one reply, 1000-20000 (default 15000).
speaker_channel	integer	Channel to caption, for jobs submitted with speaker_channels_count.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "job_id"
  ],
  "properties": {
    "format": {
      "enum": [
        "srt",
        "vtt"
      ],
      "type": "string",
      "description": "srt (default) or vtt."
    },
    "job_id": {
      "type": "string",
      "maxLength": 100,
      "minLength": 1,
      "description": "Rev.ai job id (the `id` from revai_submit_job or revai_list_jobs)."
    },
    "offset": {
      "type": "integer",
      "maximum": 100000000,
      "minimum": 0,
      "description": "Start position from the previous reply's next_offset (default 0)."
    },
    "max_chars": {
      "type": "integer",
      "maximum": 20000,
      "minimum": 1000,
      "description": "Most characters to return in one reply, 1000-20000 (default 15000)."
    },
    "speaker_channel": {
      "type": "integer",
      "maximum": 32,
      "minimum": 0,
      "description": "Channel to caption, for jobs submitted with speaker_channels_count."
    }
  }
}

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}.

read-only

Argument	Type	Description
job_id*	string	Rev.ai job id (the `id` from revai_submit_job or revai_list_jobs).

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "job_id"
  ],
  "properties": {
    "job_id": {
      "type": "string",
      "maxLength": 100,
      "minLength": 1,
      "description": "Rev.ai job id (the `id` from revai_submit_job or revai_list_jobs)."
    }
  }
}

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.

read-only

Argument	Type	Description
job_id*	string	Rev.ai job id (the `id` from revai_submit_job or revai_list_jobs).
offset	integer	Start position from the previous reply's next_offset (default 0).
max_chars	integer	Most characters to return in one reply, 1000-20000 (default 15000).

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "job_id"
  ],
  "properties": {
    "job_id": {
      "type": "string",
      "maxLength": 100,
      "minLength": 1,
      "description": "Rev.ai job id (the `id` from revai_submit_job or revai_list_jobs)."
    },
    "offset": {
      "type": "integer",
      "maximum": 100000000,
      "minimum": 0,
      "description": "Start position from the previous reply's next_offset (default 0)."
    },
    "max_chars": {
      "type": "integer",
      "maximum": 20000,
      "minimum": 1000,
      "description": "Most characters to return in one reply, 1000-20000 (default 15000)."
    }
  }
}

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}/transcript.

read-only

Argument	Type	Description
format	string	text (default) or segments.
job_id*	string	Rev.ai job id (the `id` from revai_submit_job or revai_list_jobs).
offset	integer	text: character position; segments: segment index. Use the previous reply's next_offset (default 0).
max_chars	integer	Most characters to return in one reply, 1000-20000 (default 15000).
group_channels_by	string	Multichannel jobs only: how to group words into turns.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "job_id"
  ],
  "properties": {
    "format": {
      "enum": [
        "text",
        "segments"
      ],
      "type": "string",
      "description": "text (default) or segments."
    },
    "job_id": {
      "type": "string",
      "maxLength": 100,
      "minLength": 1,
      "description": "Rev.ai job id (the `id` from revai_submit_job or revai_list_jobs)."
    },
    "offset": {
      "type": "integer",
      "maximum": 100000000,
      "minimum": 0,
      "description": "text: character position; segments: segment index. Use the previous reply's next_offset (default 0)."
    },
    "max_chars": {
      "type": "integer",
      "maximum": 20000,
      "minimum": 1000,
      "description": "Most characters to return in one reply, 1000-20000 (default 15000)."
    },
    "group_channels_by": {
      "enum": [
        "speaker",
        "sentence",
        "word"
      ],
      "type": "string",
      "description": "Multichannel jobs only: how to group words into turns."
    }
  }
}

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.

read-only

Argument	Type	Description
limit	integer	Jobs per page, 1-100 (default 20).
starting_after	string	Return jobs older than this job id (exclusive), from next_starting_after.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Jobs per page, 1-100 (default 20)."
    },
    "starting_after": {
      "type": "string",
      "maxLength": 100,
      "minLength": 1,
      "description": "Return jobs older than this job id (exclusive), from next_starting_after."
    }
  }
}

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 offered. POST /jobs.

destructive

Argument	Type	Description
language	string	Spoken language as an ISO 639-1 code (en, en-us, en-gb, es, fr, de, ...). Default en.
metadata	string	A note stored with the job and returned with it (for example your own reference).
verbatim	boolean	Keep every false start and disfluency (default true for machine jobs).
media_url*	string	Direct download URL of the audio or video file. Rev.ai fetches it; it must be reachable without login.
speakers_count	integer	Number of speakers, if known (English, Spanish, French); improves speaker labels.
filter_profanity	boolean	Mask profanity in the transcript.
forced_alignment	boolean	More accurate per-word timestamps (en, fr, it, de, es).

{ "type": "object", "$schema": "https://json-schema.org/draft/2020-12/schema", "required": [ "media_url" ], "properties": { "language": { "type": "string", "pattern": "^[a-z]{2,3}(-[a-z]{2})?(\\/[a-z]{2})?$|^auto$", "description": "Spoken language as an ISO 639-1 code (en, en-us, en-gb, es, fr, de, ...). Default en." }, "metadata": { "type": "string", "maxLength": 512, "description": "A note stored with the job and returned with it (for example your own reference)." }, "verbatim": { "type": "boolean", "description": "Keep every false start and disfluency (default true for machine jobs)." }, "media_url": { "type": "string", "pattern": "^https?:\\/\\/\\S+$", "maxLength": 4096, "description": "Direct download URL of the audio or video file. Rev.ai fetches it; it must be reachable without login." }, "speakers_count": { "type": "integer", "maximum": 100, "minimum": 1, "description": "Number of speakers, if known (English, Spanish, French); improves speaker labels." }, "filter_profanity": { "type": "boolean", "description": "Mask profanity in the transcript." }, "forced_alignment": { "type": "boolean", "description": "More accurate per-word timestamps (en, fr, it, de, es)." }, "skip_diarization": { "type": "boolean", "description": "Do not label speakers." }, "skip_punctuation": { "type": "boolean", "description": "Return words without punctuation." }, "summarization_type": { "enum": [ "paragraph", "bullets" ], "type": "string", "description": "Also create a summary, read later with revai_get_summary." }, "remove_disfluencies": { "type": "boolean", "description": "Drop 'ums' and similar fillers." }, "delete_after_seconds": { "type": "integer", "maximum": 2592000, "minimum": 0, "description": "Delete the job and its data this many seconds after it completes." }, "speaker_channels_count": { "type": "integer", "maximum": 8, "minimum": 1, "description": "Number of audio channels with one speaker each. Billed per channel." } } }