Inside Rescript: on-device Whisper transcription, voice-clone retakes, zero uploads
JeremyNguyenPhD · x · 2026-09-20
This thread follow-up links Rescript's full feature set: Whisper transcribes on-device with word-level timestamps and speaker diarization (or import SRT/VTT/JSON); deleting words cuts the matching footage, with one-click removal of filler words and silences over 0.3s; you can rewrite a fumbled line and hear it re-spoken in the original speaker's cloned voice, all rendered locally with ffmpeg — nothing is ever uploaded. Available on macOS, Windows, Linux, and web.
Related event: Rescript: Open-Source Video Editing by Editing Text(2 posts)→
More from Apps
- Pexo launches AI video agent that edits via comments, not prompts — CurieuxExplorer · 2026-09-22
- Yukan uses narrative AI to turn children's hospital journeys into adventures — LudovicDenoyer · 2026-09-22
- Googlebook laptop preview surfaces with built-in Gemini, Magic Pointer and Rambler features — xiaohu · 2026-09-22
- Sunbeam flip phone adds authenticator app, making a smartphone-free life more viable — nathan_covey · 2026-09-22
- Inside Nicolas Cole's $30M+ writing system: 3 tiers, an unmade data set, and AI as executor — Roger_M_Taylor · 2026-09-22
- Lifelogging with large language models: a hands-on writeup — mistergot · 2026-09-22