Get AI-readable transcript
get_transcriptTranscribe speech from a public video, optionally between start and end. Returns a transcript_id while processing in the background: call this tool again with transcript_id to check. When done, fetch text_url for timestamped plain text with source attribution; Markdown and JSON links are also provided. Parts without speech are listed as machine-labelled sounds with times, closed-caption style (e.g. "[cat meowing]", "[music]"). Visual content is not described. New transcription uses the normal daily quota; results last 30 days.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "get_transcript"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| end | No | Optional: end of the part to keep, in seconds (after start). | |
| url | No | Link to a public post or video (YouTube, Instagram, X / Twitter, TikTok, Bluesky, Facebook, VK, LinkedIn, Weibo). | |
| item | No | Which video of a multi-video post (1-based); see get_video_info. | |
| start | No | Optional: start of the part to keep, in seconds. | |
| transcript_id | No | Resume/check an existing transcription. |