Kyutai Pocket TTS integration

Hi all,

I wanted to try the recently released tts model from kyutai, which seems to be more efficient that kokoro and more reliable than supertonic for my hardware (ancient haswell CPU). I created a small server which uses an OpenAI compatible API to server the model in a docker environment (for instance). Works great with the OpenAI TTS custom component.

My repo can be found here https://github.com/bozakov/pocket_tts_api if you want to try it out.

pocket-tts already has a server you can send API requests to. pocket-tts serve does the trick, then you just post text=... to localhost:8000/tts.

Yes, but not openai compatible (/v1/audio/speech). this acts as a drop-in replacement for local environments.

Hey supertonix with training code and VC for free is here :