Starstruk Logo MarkStarstruk

v1.1.0

wailsapp/wailsv1.1.0Feb 16, 2026by gabrieldemarmiesse

AI Summary

This update introduces online documentation, local model loading capabilities, memory optimizations via KV cache reduction, and CLI stdin support for reading input text.

Key Highlights

  • Online documentation site added
  • Reduced memory usage via KV cache optimization
  • Ability to load local model files
  • Read input text from stdin in the CLI
  • Export and import model state functionality

New Features

  • Online documentation
  • Export model state
  • Loading local models
  • Reduced memory usage
  • CLI stdin support
  • Docker-compose with model cache persistence
  • OpenAI-compatible streaming server
  • Latency hints for AudioContext

Full Release Notes

## What's Changed

### TL;DR

* Online documentation.
* `export_model_state`
* Loading local models
* Reduced memory usage
* Read the input text from stdin in the CLI

### Not too long, I want to read

* Add .safetensors save/load to get_state_for_audio_prompt by @thataboy in https://github.com/kyutai-labs/pocket-tts/pull/69
* Clarifications regarding voices + fix missing @classmethod by @vvolhejn in https://github.com/kyutai-labs/pocket-tts/pull/86
* Basic changes to allow loading of local model files by @teddybear082 in https://github.com/kyutai-labs/pocket-tts/pull/59
* Improve consistency in variant -> config rename by @vvolhejn in https://github.com/kyutai-labs/pocket-tts/pull/87
* feat: add docker-compose.yaml with model cache persistence  by @xprabhudayal in https://github.com/kyutai-labs/pocket-tts/pull/64
* Add pocket-tts-mlx to projects list by @jishnuvenugopal in https://github.com/kyutai-labs/pocket-tts/pull/97
* Add link to OpenAI-compatible streaming server by @Shackless in https://github.com/kyutai-labs/pocket-tts/pull/96
* Reduce cached voice state + KV cache memory by @darknight054 in https://github.com/kyutai-labs/pocket-tts/pull/51
* Add "alternative implementations" by @gabrieldemarmiesse in https://github.com/kyutai-labs/pocket-tts/pull/100
* Adding possibility to read the input text from stdin in the CLI by @samuraikillers in https://github.com/kyutai-labs/pocket-tts/pull/110
* Add basic public API tests to test_python_api.py by @emirbelkahia in https://github.com/kyutai-labs/pocket-tts/pull/114
* Automated Docs Site by @sachin-sankar in https://github.com/kyutai-labs/pocket-tts/pull/101
* Use a symlink for the index page in the docs by @gabrieldemarmiesse in https://github.com/kyutai-labs/pocket-tts/pull/122
* Remove cudagraph reference by @gabrieldemarmiesse in https://github.com/kyutai-labs/pocket-tts/pull/123
* Add functions to export and import the model state for a given voice by @gabrieldemarmiesse in https://github.com/kyutai-labs/pocket-tts/pull/129
* Add latencyHint when creating AudioContext (test frontend) by @thataboy in https://github.com/kyutai-labs/pocket-tts/pull/124

## New Contributors
* @thataboy made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/69
* @teddybear082 made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/59
* @xprabhudayal made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/64
* @jishnuvenugopal made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/97
* @Shackless made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/96
* @darknight054 made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/51
* @samuraikillers made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/110
* @emirbelkahia made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/114
* @sachin-sankar made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/101

**Full Changelog**: https://github.com/kyutai-labs/pocket-tts/compare/v1.0.3...v1.1.0