Transcribe media from a URL
transcribe_mediaConverts audio from video, podcast, or social media URLs into timestamped text; uses existing captions first, then AI speech-to-text when captions are missing.
Instructions
Transcribe the audio of any video/audio URL (YouTube, TikTok, podcasts, and 1000+ sites) to text with timestamped segments. One call usually returns the finished transcript; long media returns a jobId to poll with check_transcription. By default (mode "auto") it uses the video's own captions when it has them ($0.003) and AI speech-to-text when it has none ($0.01/min). Set maxCostDollars to cap the speech-to-text charge on long media; mode "captions" never runs speech-to-text. Runs the same job as POST /transcribe with mode "auto" and wait in the REST API; to build transcription into the user's app, call get_integration_guide.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"url": "<url>"
},
"name": "transcribe_media"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Media page URL, e.g. https://www.youtube.com/watch?v=... | |
| mode | No | auto (default): captions, then AI speech-to-text if there are none. captions: captions only ($0.003), fails with a cost quote if there are none. ai: always AI speech-to-text ($0.01/min) | |
| language | No | ISO language hint, e.g. "en" | |
| provider | No | Same as mode "ai": always use AI speech-to-text, even when the media has captions ($0.01/min) | |
| maxCostDollars | No | Abort with a quote if the estimated speech-to-text cost exceeds this cap |