Transcribe Audio or Video
Run this in GezelNothing opened? Opening from this site needs the latest Gezel. Get Gezel
Convert an audio or video recording into an accurate, readable transcript using speech-to-text, with speaker labels and timestamps. Scopes the output format, speaker-labeling, and timestamp granularity FIRST so the transcript is usable downstream (search, subtitles, minutes), then transcribes the full recording end-to-end, then verifies coverage against the recording's duration and checks for dropped segments. The scope-first ordering matters because deciding timestamp cadence and speaker handling up front is what separates a clean, searchable transcript from a wall of unattributed text.
How it runs
| # | Step | Who runs it | What happens |
|---|---|---|---|
| 1 | Scope the transcript | Planner | format, speaker labels, timestamp cadence, glossary |
| 2 | Transcribe the recording | Developer | run STT over the full file, label speakers, timestamp |
| 3 | Evaluate | Reviewer | Grade the deliverable against every acceptance criterion. All pass → finish; any fail → loop back and fix the gap. |
| 4 | Finish | Developer | All acceptance criteria met. Stamp a short summary and report DONE. |
Say something like "transcribe this audio" or "transcribe a video" or "speech to text" or "get a transcript" or "convert recording to text" in chat to start it.