Starstruk Logo MarkStarstruk

v0.7.2

juliangarnier/animev0.7.2May 25, 2026by KoljaB

AI Summary

Optimizes PocketTTS performance using persistent workers and introduces streaming controls.

Key Highlights

  • Persistent worker thread for synthesis
  • Serial streaming to fix memory retention on Windows/Torch CPU
  • Streaming controls: streaming, max_tokens, and frames_after_eos
  • Custom model configs via model_config

New Features

  • Persistent worker thread
  • Streaming controls
  • Custom model configuration
  • Voice state caching support

Full Release Notes

# RealtimeTTS v0.7.2

### Improvements

* Reworked `PocketTTSEngine` to run synthesis through a persistent worker thread.
* Patched PocketTTS short-text streaming to decode serially, avoiding Windows/Torch CPU memory retention during repeated short generations.
* Added PocketTTS streaming controls: `streaming`, `max_tokens`, and `frames_after_eos`.
* Added support for custom PocketTTS model configs via `model_config`.
* Added support for cached voice states through `PocketTTSVoice(state_path=...)`.
* Added optional voice-state caching through `voice_cache_dir` and `cache_voice_states`.
* Improved PocketTTS audio conversion, queueing, duration tracking, and shutdown cleanup.

### Packaging

* Bumped package version to `0.7.2`.
* Set the PocketTTS dependency to `pocket-tts>=2.1.0`.
* Refreshed explicit dependency versions, including `stream2sentence`, `openai`, `elevenlabs`, `edge-tts`, `requests`, `cartesia`, `camb-sdk`, `omnivoice`, and `typecast-python`.

### Documentation

* Added PocketTTS runtime notes for the persistent worker and serial streaming behavior.
* Cleaned up the README support section.