Very cool! starred and on my reading list. Would love to chat and share notes, if you'd like

nicktikhonov • yesterday at 10:58 PM • 2 replies • view on HN

You may be interested in gemini-2.5-flash-preview-tts

Text in, audio out, so you can merge in a single step LLM+TTS (streamable)

Also consider using Cerebras' inference APIs. They released a voice demo a while back and the latency of their model inference is insane.

➕ show 1 reply

alt Hacker News