[taosx]

Looks very nice, saved it for later. Last week, I worked on implementing always-on speech-to-text functionality for automating tasks. I've made significant progress, achieving decent accuracy, but I imposed some self-imposed constraints to implement certain parts from scratch to deliver a single binary deployable solution, which means I still have work to do (audio processing is new territory for me). However, I'm optimistic about its potential.

That being said, I think the more straightforward approach would be to utilize an existing library like https://github.com/collabora/WhisperLive/ within a Docker container. This way, you can call it via WebSocket and integrate it with my LLM, which could also serve as a nice feature in your product.

[xyc]

Thanks! lmk when/if you wanna give it a spin as free trial hasn't been updated with the latest but I'll try to do it this week.

I've actually been playing around with speech to text recently. Thank you for the pointer, docker is a bit too heavy to deploy for desktop app use case but it's good to know about the repo. Building binaries with Pyinstaller could be an option though.

Real time transcription seems a bit complicated as it involves VAD so a feasible path for me is to first ship simple transcription with whisper.cpp. large-v3-turbo looks fast enough :D

[taosx]

Yes it's fast enough, especially if you don't need something live.