v2.0.0

## New models! 🎉 🎉 🎉 

<img width="453" height="496" alt="pocket-tts-multilingual-v2 (2)" src="https://github.com/user-attachments/assets/fbb5beb6-c4bb-404b-99a7-5bb4c13451b8" />

Credit: @vvolhejn 

This release notably includes new models. We now have a `--language` argument to select the pre-trained model from the cli and a `language=` argument in `TTSModel.load_model()`. Here is the list of all available models/languages:

* `english_2026-01`: The only model that was available until now. 6 layers.
* `english_2026-04`: The new and improved english model. Supports better short sentences and has better voice cloning. 6 layers.
* `english`: This is just an alias for `english_2026-04`.
* `italian`: Our new pocket-tts in italian! 6 layers.
* `italian_24l`: The undistilled italian model. We would love reports if you find bugs that are present in the `italian` model but not in the `italian_24l` model. 24 layers.
* `german`: Our new pocket-tts in german! 6 layers.
* `german_24l`: The undistilled german model. We would love reports if you find bugs that are present in the `german` model but not in the `german_24l` model. 24 layers.
* `spanish`: Our new pocket-tts in spanish! 6 layers.
* `spanish_24l`: The undistilled spanish model. We would love reports if you find bugs that are present in the `spanish` model but not in the `spanish_24l` model. 24 layers.
* `portuguese`: Our new pocket-tts in portuguese! 6 layers.
* `portuguese_24l`: The undistilled portuguese model. We would love reports if you find bugs that are present in the `portuguese` model but not in the `portuguese_24l` model. 24 layers.
* `french_24l`: The undistilled french model. The distillation of the french model has been more painful than anticipated due to the data quality. While we fix those issue, we want to unblock the french pocket-tts community, which is why we release the undistilled version here. 24 layers.

If the 24 layers are too slow to run in real-time on your CPU, you can try the new `--quantize` option! You can expect ~30% perf improvements in most cases.

The pre-defined voices are all english. For other languages, we recommend using the voice cloning and use a voice prompt that correspond to your language.

## Note for maintainers of alternative implementations

This section should be especially helpful to @LaurentMazare @KevinAHM @babybirdprd @ekzhang @jishnuvenugopal @VolgaGerm @csukuangfj @TheAjaykrishnanR 

The pocket-tts community has been amazing! We were blown away by the number of alternative implementation of pocket-tts in other languages and frameworks! We want to make it easy for them to adapt their code to the new models. I added comments to the [commit that did architecture changes](https://github.com/kyutai-labs/pocket-tts/commit/c90fc8ced65ce71b99b610969704b01e322df05f). If you report the changes done next to each comment, that should be enough to make your alternative implementation work!

Here is the list
* [Beginning of sequence weight](https://github.com/kyutai-labs/pocket-tts/commit/c90fc8ced65ce71b99b610969704b01e322df05f#r183012387)
* [Upsample and downsample take more args](https://github.com/kyutai-labs/pocket-tts/commit/c90fc8ced65ce71b99b610969704b01e322df05f#r183012523)
* [Speaker proj weight have the dimensions configurable](https://github.com/kyutai-labs/pocket-tts/commit/c90fc8ced65ce71b99b610969704b01e322df05f#r183012639)
* [Optional: a trick to make sure mimi is working](https://github.com/kyutai-labs/pocket-tts/commit/c90fc8ced65ce71b99b610969704b01e322df05f#r183012847)
* [Prompting a new beginning of sequence before the voice prompt](https://github.com/kyutai-labs/pocket-tts/commit/c90fc8ced65ce71b99b610969704b01e322df05f#r183012905)
* [Making the downsample more flexible](https://github.com/kyutai-labs/pocket-tts/commit/c90fc8ced65ce71b99b610969704b01e322df05f#r183012944)
* [Making the upsample more flexible](https://github.com/kyutai-labs/pocket-tts/commit/c90fc8ced65ce71b99b610969704b01e322df05f#r183012960)

## Notable pull requests:
* Changed the implementation to fuse the transformers by @darknight054 in https://github.com/kyutai-labs/pocket-tts/pull/85
* Raise minimum huggingface_hub to 0.13.0 for consistent offline behavior by @joshwhiton in https://github.com/kyutai-labs/pocket-tts/pull/137
* Add int8 dynamic quantization support by @nabil-tazi in https://github.com/kyutai-labs/pocket-tts/pull/147
* Split long sentences on commas to prevent skipped words by @costajohnt in https://github.com/kyutai-labs/pocket-tts/pull/143
* Add french, italian, portuguese, spanish, german by @gabrieldemarmiesse in https://github.com/kyutai-labs/pocket-tts/pull/155

## New Contributors
* @ai-joe-git made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/136
* @joshwhiton made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/137
* @alkmei made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/138
* @dooart made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/139
* @tonelord made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/140
* @VolgaGerm made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/142
* @csukuangfj made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/150
* @nabil-tazi made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/147
* @costajohnt made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/143
* @markd89 made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/157
* @TheAjaykrishnanR made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/159
* @dodgyrabbit made their first contribution in https://github.com/kyutai-labs/pocket-tts/pull/160


### Many thanks to the community for being so awesome! ❤️ 

**Full Changelog**: https://github.com/kyutai-labs/pocket-tts/compare/v1.1.1...v2.0.0