Search transcripts
search_transcriptsKeyword search over full transcripts, returning matching paragraphs with a snippet, speaker, timestamp and a link to the exact paragraph. Use when search_facts finds nothing or you need the surrounding conversation: call get_transcript with show_slug, episode_slug and offset set to the hit's paragraph.
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": {
"query": "<query>"
},
"name": "search_transcripts"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| show | No | Only search this show: slug or title from list_shows | |
| limit | No | How many to return, 1-20, default 10 | |
| query | Yes | Keywords, matched literally (stemmed full-text search, not semantic). Best with 2-4 distinctive words such as names, companies or terms, e.g. "Jensen Huang data centers". Filler and question words are ignored; results matching every keyword come first, then results matching some of them. | |
| offset | No | How many to skip, default 0. Pass next_offset from the previous page to get the next page. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| hint | No | ||
| note | No | ||
| match | No | ||
| total | Yes | ||
| offset | Yes | ||
| results | Yes | ||
| next_offset | No |