Spaces:

---

smolagents

/

hf-realtime-voice

like 543

Running

Hi @andito @A-Mahla @abidlabs Can u guide on deploying the qwen 3 tts , to acheive the same kind of fast inference ,i have figured out the the tpm via groq or cerebras from the repo, but i want to host this on the cloud for my personal voice agent , the latency is too low here compared to closed source model ,Can you please help me