v0.5.3

stepfun-ai/Step-Audiov0.5.3Apr 19, 2025by KoljaB

AI Summary

This update introduces configurable silence control within the stream, migrates KokoroEngine to KokoroVoice, and enhances OrpheusEngine with model selection and stop-on-demand improvements.

Key Highlights

Configurable silence durations (comma, sentence, default) moved to TextToAudioStream
KokoroEngine migration to KokoroVoice
OrpheusEngine now allows model selection and improved stop-on-demand checks
Introduction of SafePipe for more reliable inter-process communication

New Features

Configurable silence control
KokoroEngine using KokoroVoice
OrpheusEngine model selection

Full Release Notes

# RealtimeTTS v0.5.3 Release Notes

**Enhancements & Changes:**
- **Silence Control**: Moved silence‑insertion out of CoquiEngine into `TextToAudioStream`; introduced configurable `comma`, `sentence`, and `default` silence durations in play- and play-async methods.  
- **KokoroEngine**: Uses KokoroVoice now. #303 (thank you)
- **OrpheusEngine**: Lets you pick model now and has improved stop‑on‑demand checks.  
- **More Thread‑Safe Pipes (?)**: Added `SafePipe` for what I hope is more reliable inter‑process comm in CoquiEngine (needs to be tested more).