Ask HN: What's the best realtime, local, TTS solution? Live call interpretation

Wright007 | 2026-02-15 18:04 UTC | source

6 points | 2 comments | original link

So I'm trying to build a system that listens to calls as they're happening. All implementations antigravity/codex/cursor throws out have been really janky and ineffective. Spent a couple days prompt engineering without finding an elegant solution. Anybody have insights?

Comments

ahmedgagan | 2026-02-15 18:39 UTC

What about recording the audio of your output? device and then transcribing it

bruce343434 | 2026-02-18 00:30 UTC

https://alphacephei.com/vosk/install

> We also provide a websocket server and grpc server which can be used in telephony and other applications. With bigger models adapted for 8khz audio it provides more accuracy.