Prince Canuma
Prince Canuma
Thanks @chigkim! @BenLumenDigital is on it 🚀
> For STT, there are also [voxtral](https://mistral.ai/news/voxtral) small and mini that seem to be quite good Voxtral is done ✅ since v0.2.5
> It would be great to have [microsoft/VibeVoice.](https://huggingface.co/microsoft/VibeVoice-Large) On the pipeline, will try to get it working this week
@BuffMcBigHuge On it 🚀
> FWIW I was looking at MLX Swift again recently and it might be easier to just pull this in -- it's pretty small and has minimal dependencies that will...
Sorry for that. The speech to speech demo is due for a remake. You can use our pipecat integration for the time being: https://x.com/kwindla/status/1960447000132116562
Hey @4davelo! Thank you very much! Yes, very few VLMs can do structured outputs so we leave that to the developer using to handle. If you have a good idea...
Hi @Lewiscowles1986 You came to the right place! How can I help?
Hey Javi, Video generate should deprecated and moved into generate Chat_UI needs to be fixed
Hey Thank you very much! Not yet, but if you share your use case I will see what I can do :)