podcast hosted
Podcast transcript chunks, rolling ~1yr window (observed coverage starts ~Apr 2025; oldest hits found 2025-04-28). Things said, never written.
- tier
- hosted
- category
- audio & transcripts
- coverage
- 2026-07
- ranking
- bm25
- knobs
- q, limit, before, after, show, source, min_popularity, min_views, rank
Guidance
BM25 over transcript chunks. A hit is one chunk; meta carries show_title and start_sec/end_sec timestamps into the audio at url. Filter with show, source, min_popularity, min_views, before/after (ISO dates). Note: ep_views is currently 0 on all hits upstream, so min_views>0 returns nothing; leave it unset for now. Coverage note: the index is a rolling ~1-year window: do not expect audio older than ~Apr 2025. text is capped at 1200 chars; the full audio is at url with start_sec/end_sec in meta.
Usage
The public endpoint is not live yet. Keys are invite-only during beta; contact shapeandfact+takedown@gmail.com.
Plain HTTP:
curl -s https://bipsearch.ai/search \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"corpus": "podcast", "q": "federal reserve rate decision", "limit": 5}'
Or via MCP, after adding the server once (see quickstart):
# after: claude mcp add --transport http bipsearch https://bipsearch.ai/mcp \
# --header "Authorization: Bearer YOUR_KEY"
list_corpora()
search(corpus="podcast", q="federal reserve rate decision", limit=5)