Show HN: Gdańsk AI – full stack AI voice chatbot

Post by ddnb » Sat, Aug 05, 2023, 7:54 AM UTC

famouswaffles wrote: post #20

a2128 wrote: post #18

I've always wondered if there's a better way of making voice assistants. With this stack, the AI will not be able to answer "what is this sound?", or give you UK-based information because it picked up on your British accent. It's bottlenecked by text. A model that can understand audio as input, and output audio directly, could be so much more powerful

Sure there's a better way. https://google-research.github.io/seanet/audiopalm/examples/ There's no reason autoregressive LMs can't be used to model audio data.

Post by nielsinho » Sat, Aug 05, 2023, 9:31 AM UTC

kjok wrote: post #24

nielsinho wrote: post #17

Earlier quoted context omitted.

TorToiSe ( https://github.com/neonbjb/tortoise-tts ) produces the best quality speech of any freely available model. However, its long inference times makes it impractical for voice chatbots like Gdansk.

What's the reason for the high inference latency? Any ideas on how this could be improved?

Post by yu3zhou4 » Tue, Aug 08, 2023, 1:36 PM UTC

yu3zhou4 wrote: post #15

quantum-crt wrote: post #2

Looks cool! Do you have a hosted version anywhere we could play around with?

Demo is live! https://bibop.app/ Let me know if there are any troubles running it. It works under Google Chrome