✛ Media

Transcript Intelligence

Send a direct link to an audio or video file, or the file itself. You get the transcript with timestamps as JSON, SRT and VTT. Clips up to 5 minutes are answered in the same call; longer recordings, up to three hours, are queued and usually finish within minutes, with a 24-hour promise: if we miss it, it's free. Pay per second of audio. On the queued call, set speakers to true to label who said each segment (S1, S2, ...).

Queue a transcription. max_minutes is the most the audio may last; you are charged only for the seconds it actually runs.

POST/v1/transcript/transcribe
Try it ↓

Answers 202 with a job_id. Poll GET /v1/jobs/{id} (free) or pass callback_url. How long jobs work.

Price
$0.000132 per second · REST and MCP
RapidAPI
$0.000165 per second · listing at launch
Per call
up to 3 hours of audio · at most $1.4256
Returns
application/json
MCP tool
transcript_intel_transcribe

Request body

FieldTypeDescription
max_minutesrequiredintegerThe most the audio can last. This much is held; only the seconds it measures are charged. Longer audio is refused and refunded.
audio_urlstringDirect https link to an audio or video file (up to 350 MB). Not a YouTube or TikTok page.
audio_base64stringThe file itself, base64, when it fits in the 2 MB request limit.
languagestringLanguage code such as "en" or "ro"; detected when left out.
speakersbooleanLabel who said each segment (S1, S2, ...). Slower; same price.
callback_urlstringTold the job's id and status when it ends, signed with your webhook secret.
example
curl https://readymadeapi.com/v1/transcript/transcribe \
  -H "Authorization: Bearer $READYMADE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio_url": "https://readymadeapi.com/samples/voice-note.mp3",
    "max_minutes": 60
  }'
What comes backAt once, from this call (202)
{
  "job_id": "01a1f553-8b2b-7487-b36c-93e3bd7be737",
  "status": "queued",
  "status_url": "/v1/jobs/01a1f553-8b2b-7487-b36c-93e3bd7be737",
  "result_url": "/v1/jobs/01a1f553-8b2b-7487-b36c-93e3bd7be737/result"
}
Later, from GET /v1/jobs/{id}, when the job is done
{
  "job_id": "01a1f553-8b2b-7487-b36c-93e3bd7be737",
  "status": "succeeded",
  "late": false,
  "deadline": "2026-11-20T19:40:55.463853Z",
  "completed_at": "2026-11-19T19:40:56.003566Z",
  "error": null,
  "result": {
    "text": "Hi, this is a short voice note. Please move our meeting to Thursday at 10 and bring the signed contract.",
    "language": "en",
    "segments": [
      {
        "end": 5.98,
        "text": "Hi, this is a short voice note. Please move our meeting to Thursday at 10 and bring the signed contract.",
        "start": 0.0
      }
    ],
    "duration_s": 6.525,
    "srt": "1\n00:00:00,000 --> 00:00:05,980\nHi, this is a short voice note. Please move our meeting to Thursday at 10 and bring the signed contract.\n\n",
    "vtt": "WEBVTT\n\n00:00:00.000 --> 00:00:05.980\nHi, this is a short voice note. Please move our meeting to Thursday at 10 and bring the signed contract.\n\n"
  }
}

Try it · $0.000132 per second, paid from your credit

No key yet? Get an API key · it works for every API.

Transcribe a short clip, up to 5 minutes and 15 MB, and get text, timestamps, SRT and VTT in the same call. max_seconds is the most the clip may last; you are charged only for the seconds it actually runs.

POST/v1/transcript/instant
Try it ↓
Price
$0.000132 per second · REST and MCP
RapidAPI
$0.000165 per second · listing at launch
Per call
up to 5 minutes of audio · at most $0.0396
Returns
application/json
MCP tool
transcript_intel_transcribe_now

Request body

FieldTypeDescription
audio_urlstringDirect https link to an audio or video file, up to 15 MB. Not a YouTube or TikTok page.
audio_base64stringThe file itself, base64, when it fits in the 2 MB request limit.
max_secondsintegerThe most the clip can last, 1 to 300, 120 if left out. This much is held; only the seconds it measures are charged. A longer clip is refused and not charged.
languagestringLanguage code such as "en" or "ro"; detected when left out.
example
curl https://readymadeapi.com/v1/transcript/instant \
  -H "Authorization: Bearer $READYMADE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio_url": "https://readymadeapi.com/samples/voice-note.mp3",
    "max_seconds": 60
  }'
What comes back
{
  "text": "Hi, this is a short voice note. Please move our meeting to Thursday at 10 and bring the signed contract.",
  "language": "en",
  "duration_s": 6.525,
  "segments": [
    {
      "start": 0.0,
      "end": 5.98,
      "text": "Hi, this is a short voice note. Please move our meeting to Thursday at 10 and bring the signed contract."
    }
  ],
  "srt": "1\n00:00:00,000 --> 00:00:05,980\nHi, this is a short voice note. Please move our meeting to Thursday at 10 and bring the signed contract.\n\n",
  "vtt": "WEBVTT\n\n00:00:00.000 --> 00:00:05.980\nHi, this is a short voice note. Please move our meeting to Thursday at 10 and bring the signed contract.\n\n"
}

Try it · $0.000132 per second, paid from your credit

No key yet? Get an API key · it works for every API.

Use it from an agent

Every endpoint above is also an MCP tool. Add the server to Claude, Cursor or any MCP client and the tools appear with their prices; calls draw from the same credit.

Connect guide · OpenAPI 3.1 spec · llms.txt

mcp config
{
  "mcpServers": {
    "readymade": {
      "type": "http",
      "url": "https://readymadeapi.com/mcp",
      "headers": {
        "Authorization": "Bearer ${READYMADE_KEY}"
      }
    }
  }
}