steve-adminandClaude Sonnet 5
a65532f3b2
--instruction passes through to MOSS-TTS's build_user_message (confirmed to work for emotion in earlier testing) so callers can steer per-line delivery. --seed enables reproducible generation, currently the only way to get determinism out of this pipeline since MOSS-TTS/AuK don't use a fixed-seed workflow the way Qwen3 did. Needed for a downstream per-line episode-generation pipeline (character cards + emotion-tagged script lines). Co-Authored-By: Claude Sonnet 5 <[email protected]> Claude-Session: https://claude.ai/code/session_01Y1oQ4h4WE4R9KRvMQLr5Ey
audio-demo
Audio processing demos: WhisperX, Demucs, and TTS technology proofs-of-concept.
Structure
whisperx/— speech-to-text with word-level alignment and diarizationdemucs/— source separation (vocals/instrumentals stem splitting)tts/— text-to-speech service demos (voice cloning via MOSS-TTS)auk/— voice editing demos (emotion/pitch/speed/content editing on existing recordings, as opposed totts/'s clone-and-generate approach)webui/— interactive pipeline studio chaining demucs -> AuK -> MOSS-TTS with previews
Each subdirectory has its own README with setup and run instructions.
Requirements
Some demos are GPU-accelerated and are best run on a CUDA-capable machine (e.g. an RTX 3090).
Planned: full audio-translation demo
Chain the three demos together on media-files/ into an end-to-end pipeline:
demucs— separate the source clip into vocals / instrumental stemswhisperx— transcribe the isolated vocal stem, then machine-translate the transcripttts— clone the original speaker's voice (from the isolated vocal stem) and synthesize the translated text in that voice, then remix with the original instrumental stem
Stem separation and transcription are already working end to end (see demucs/README.md and
whisperx/README.md); translation and voice-cloning TTS are not yet implemented.