Pureframe AI API Documentation

Restrict a query to spoken words with modes=transcript. This searches transcribed speech only: visual content, scene labels, and on-screen text are excluded from matching.

curl -X POST https://api.pureframe.ai/v1/search \
  -H "Authorization: Bearer pf_..." \
  -F "query=pricing discussion" \
  -F "modes=transcript" \
  -F "collection_id=col_abc123"

How matching works

Transcript search works best when your query uses words that are likely to appear in the speech. For example, pricing objection is more likely to match a segment containing those terms than one that expresses the same idea with different wording. Use Search signals to compare transcript and visual matching.

When to restrict to transcript-only

You know that someone said a specific phrase.
You are building a search experience for meetings, lectures, interviews, or calls.
Visual matches would be irrelevant or distracting.

Use the default combined search when either visual or spoken content could identify the segment.