Vance IngallsandClaude Opus 4.6 07f431669e feat(cli): add whisper transcription to init flow ...

New modules:
- whisper/manager.ts: download/cache whisper.cpp binary + model
  (~/.cache/hyperframes/whisper/)
- whisper/transcribe.ts: extract audio, run whisper, save transcript.json

Init flow changes:
- "Got a video or audio file?" now accepts audio-only files (mp3, wav, m4a)
- "Generate captions from audio?" prompt after file selection
- Transcription produces transcript.json in project root
- Graceful fallback if whisper/ffmpeg unavailable

Supports: macOS ARM64/x86, Linux x86_64. Downloads whisper.cpp v1.7.3
from GitHub releases and ggml-base.en model from Hugging Face.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-03-26 18:03:27 +00:00

..

cli

feat(cli): add whisper transcription to init flow

2026-03-26 18:03:27 +00:00

core

fix(ci): remove prepublishOnly build scripts (#50)

2026-03-25 19:11:37 +01:00

engine

chore: release v0.1.2 (#32)

2026-03-24 06:06:12 +01:00

producer

fix(producer): add margin reset when wrapping HTML fragments (#55)

2026-03-26 04:48:47 +01:00

studio

chore: release v0.1.2 (#32)

2026-03-24 06:06:12 +01:00