The voices sound really pleasant and realistic. Sadly it doesn't support SIP. I found forwarding streams with websocket for phone calls tend to introduce some unwanted latency that's quite noticeable in a conversation. I've found a lot of success with GPT-live-1 so far, but the generated voices are lacking something I can't put my finger on.
ha-shine · · focus · HN ↗
mattstir · · focus · HN ↗