Feb 17

Native timecoded transcripts for editing

I’m using Superwhisper to transcribe long-form audio (podcasts, interviews, etc.) and then edit the content down in a DAW (Logic, Pro Tools, etc.).Right now, Superwhisper already produces great transcripts and has access to internal timing information (as seen in the exported meta.json with start/end per segment), but there is no simple way to get a human‑readable, timecoded transcript out of the app. This makes fast editing and collaboration harder than it needs to be.What I’d love to see:An option in “Transcribe File” to export a transcript with native timecodes per segment.Formats like:Subtitle‑style (SRT / VTT), and/orSimple text like [HH:MM:SS.mmm – HH:MM:SS.mmm] transcript line…Timecodes should be derived directly from Superwhisper’s own timing data (no AI guessing, no hallucinated timestamps).Why this matters:Huge for podcast and video editors who need to jump quickly to specific moments in the audio.Makes it easy to create an edit decision list / paper edit: you mark which timecoded lines to keep or cut, then apply those cuts in the DAW.Great for teams: a producer can work from the transcript and hand precise timecodes to an editor.Ideal UX:Right‑click audio file → “Transcribe with Superwhisper” → choose a mode → when it’s done, I can:Copy a timecoded transcript to clipboard, orSave a .txt / .srt / .vtt file with real timecodes.Superwhisper is already an amazing tool for creators. Adding native, reliable timecoded transcripts would make it a killer app for podcast and video production workflows.

Pending