An agent-drivable CLI that turns a content channel into an audiobook — four pipelines in one binary: Instagram reels transcribed on GPU Whisper, YouTube captions, agent-authored book drafting, and self-hosted vLLM-Omni narration to finished MP3s, all resumable against a SQLite ground truth.
- Four pipelines, one binary — Instagram (gallery-dl + GPU Whisper), YouTube captions, book drafting, audiobook narration
- Resumable by design — SQLite ground truth with manifest verification, plus status, verify and retry commands
- GPU transcription — batched faster-whisper fed by a stealth browser profile
- Self-hosted voice — vLLM-Omni (VoxCPM2) narration to finished MP3s
- Preflight discipline — a doctor command gates every run on a clean environment
pythonfaster-whisperclitts
Closed-source project — media, details, and demo available on request.