Show HN: A fast OSS voice assistant
swift-ai.vercel.app
Show HN: A fast OSS voice assistant
1–10 of 31 posts
Re: Show HN: A fast OSS voice assistant
#2(Not your server, not your code!)
Re: Show HN: A fast OSS voice assistant
#3Is it really open source then, even though (as far as I can tell) Whisper and Llama have open weights but not open data, and that speech synthesis thing is seemingly fully proprietary?
Loving the new wave of ultrafast voice assistants though, and your execution in particular is very good.
Re: Show HN: A fast OSS voice assistant
#4Re: Show HN: A fast OSS voice assistant
#5I haven't been using LLM-powered voice assistants much since I usually prefer text. One thing I noticed playing around with this demo is that the conversational uncanny valley becomes much more apparent when you're speaking with the LLM.
That's not a knock on this project, but wow it's something I want to think about more.
Thanks for sharing!
Re: Show HN: A fast OSS voice assistant
#6Re: Show HN: A fast OSS voice assistant
#7I take it that Show HN is not just about the creation but also about the creator and the journey behind what’s being shown.
Re: Show HN: A fast OSS voice assistant
#8So who made this? Vercel? I know this is being posted by the Vercel CEO. Did you “commission” this as an ad? Or was it maybe built by a customer, and you helped him get visibility? What’s the story? I take it that Show HN is not just about the creation but also about the creator and the journey behind what’s being shown.
> Show HN is for something you've made that other people can play with.
...
> The project must be something you've worked on personally and which you're around to discuss.
---
OP doesn't spam Show HN or anything, so probably worth giving the benefit of the doubt. If it doesn't comply they'll probably realize and fix it.
Re: Show HN: A fast OSS voice assistant
#9So OSS frontend and proprietary backend is open source?
Re: Show HN: A fast OSS voice assistant
#10This looks cool, but I would have said it's more like an OSS frontend to some closed-source proprietary cloud stuff, which adds up to a voice assistant. (Not your server, not your code!)