Make show notes from a transcript
make_show_notesUse this after transcribe_media, or when the user has a transcript, for "write show notes for this episode", "add YouTube chapters to my video", "pull the best quotes". Pass exactly one of transcript_id (with library_id when transcribe_media gave one), transcript (the text, or an SRT or VTT file) or url (the same link). Returns a summary, chapters with times and YouTube chapter lines, up to 3 quotes with times, keywords, Markdown show notes and post_topic for draft_posts. Fixed rules pick sentences as spoken; no model, no cost.
Example tool call
This call uses example arguments supplied in the tool’s input schema.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"url": "https://www.youtube.com/watch?v=jNQXAC9IVRw"
},
"name": "make_show_notes"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | The same link given to transcribe_media: a public YouTube, TikTok, Instagram or other social video, or a direct audio or video file link. It is transcribed again under Transcript Kit's daily minutes; transcript_id costs nothing. | |
| title | No | Episode or video title for the notes (default: the transcript's title). | |
| library_id | No | The library_id that same transcribe_media answer gave, such as lib_9b6a98861ea4f54bff8f5cf1. Pass it with transcript_id when the answer had one. | |
| transcript | No | The transcript itself: plain text, or the text of an SRT or WebVTT file (its times become chapter times), up to 60000 characters. | |
| transcript_id | No | The transcript_id a transcribe_media answer gave, such as tr_a6f8c87a9b2eb748. Give exactly one of transcript_id, transcript or url. | |
| confirm_rights | No | With url only, as for transcribe_media: true only after the user says they own the recording or may use it. A public social video needs none. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| note | Yes | ||
| as_of | Yes | ||
| notes | Yes | ||
| title | Yes | ||
| source | Yes | ||
| status | Yes | ok: the notes are ready. A refused call returns an error text such as "transcript_not_found: ..." that says what to do next. | |
| summary | Yes | 3 to 5 sentences from the transcript that carry its most repeated words, in spoken order. | |
| chapters | Yes | ||
| keywords | Yes | The words said most often, for tags. | |
| language | Yes | Spoken language as an ISO 639-1 code; null for pasted text. | |
| key_quotes | Yes | Up to 3 sentences of 8 to 35 words, as spoken, for a quote card or a post. | |
| post_topic | Yes | The title and summary in one paragraph, as the topic of a post about the episode. | |
| word_count | Yes | ||
| duration_seconds | Yes | Length of the recording; null when the transcript had no times. | |
| untrusted_source | Yes | ||
| youtube_chapters | Yes | The chapters as lines to paste into a YouTube description (0:00 first, 3 or more, each 10 s or longer); null when that is not possible. | |
| description_markdown | Yes | Summary, chapters, quotes and keywords as Markdown to paste under the episode or video. Markdown signs in the spoken text are escaped, but a bare www. or http(s):// address or an email address in it is not, so it becomes a link where GitHub Flavored Markdown is rendered: check links before publishing. |