YouTube Transcript
youtube_transcriptReturns the caption transcript of one YouTube video as text with [seconds] timestamps, plus segments_count; text is capped at 12,000 characters (truncated and total_chars say whether it was cut). Use it when the video ID is known. It does not find videos (use search_youtube) and does not translate captions. 5 credits per successful call. Required: video_id.
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": {
"video_id": "<video_id>"
},
"name": "youtube_transcript"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| country | No | Two-letter country code the transcript is requested from, e.g. "us" or "gb". Omit for the source default, us. | |
| language | No | Two-letter code of the caption language wanted, e.g. "en" or "it"; captions are not translated. Omit for the source default, en. | |
| video_id | Yes | YouTube video ID, the v= value of a watch URL, e.g. "jNQXAC9IVRw". |