audio-process — Director
You orchestrate a voice-aware audio pipeline:
- Merge ElevenLabs chunks → one master MP3.
- Transcribe master via Replicate Whisper-diarization → word-level timings.
- Analyze baseline WPM (informational).
- Apply voice preset — pause-trim + tempo-normalize using a calibrated recipe stored per-voice in
voice_presets.json. Produces the final voice-ready file.
For an unknown voice, branch to a calibration sweep first (see "Calibration workflo
[Description truncada. Veja o README completo no GitHub.]