Rev.ai MCP by usefulapi

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

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

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.

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

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

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

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.

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

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}.

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

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.

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

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.

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

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.

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