Semantic search

Semantic search across your interview archive

Type the idea you're chasing, not the exact words. The index ranks every line in your project by meaning and returns the file, timecode, and speaker. Try the demo on a sample project below.

Try it now

A working sandbox. No sign-up, no project. Sample data only.

  • Searches by meaning, not just keyword. Finds the line even when you can't recall the exact phrasing.
  • Concept extraction surfaces recurring themes across hundreds of hours of material.
  • Chat with your archive: describe the idea and the chat locates the moment, regardless of exact phrasing, surfacing causality and connections you would otherwise miss.
  • Indexing runs in the background as new transcripts land. No manual step needed.
SEMANTIC SEARCH · SAMPLE PROJECT
demo
0 hits

Try a preset query or type your own.

How it works

Three steps from raw material to result.

STEP 01
Project archive indexing
Day 04 · Marin Interviewindexed
Day 09 · Reyes Cutawayindexed
Day 11 · Thorne Sessionindexed
Day 17 · Ensemblerunning
New files indexed automatically as they land
Auto-index in the background

Each transcript is broken into passages and indexed for meaning as soon as it lands. The project archive grows automatically with every new file.

STEP 02
when the numbers stopped making sense
ELENA M."The numbers stopped making sense."98%
DAVID R."The math wasn't adding up."91%
MARCUS T."The figures no longer tracked."84%
Query by meaning

Type the idea, not the exact words. The search ranks every passage in your archive by how closely it matches what you're looking for.

STEP 03
Jumped to
Day 04 · Marin Interview.wav
00:24:11
ELENA M. · 00:24:11

The numbers stopped making sense. That was the moment we knew.

Jump straight to the moment

Every result carries the file, timecode, and speaker. Click any hit to open the player at that line.

Frequently asked questions

How is this different from keyword search?

Keyword search needs the exact word. Semantic search ranks lines by meaning. A query like "when the numbers stopped making sense" finds "the math wasn't adding up" too.

What's under the hood?

Each transcript passage is encoded into a meaning-based index. Your query is encoded the same way and ranked by how closely it matches, with a small reranking pass on the top results.

Can I search across all my projects at once?

No. Semantic search is scoped to a single project to keep results focused and to respect collaborator boundaries. Use the project switcher to move between archives.

Do I need to re-index when I add a file?

No. New transcripts are indexed automatically in the background as soon as they land. You'll see a small progress indicator on the project page until indexing completes.

Is there a chat interface on top of search?

Yes. You can ask questions about your project and get answers grounded in cited transcript passages, with every citation showing speaker, file, and timecode.

Related capabilities

Further reading

Background guides and comparisons.

Put semantic search to work on your project.

Start free with 5 minutes of AI transcription a month. Or book a personalised walkthrough with the team.