Hey HN -<p>I'm a co-founder at Fixie, a Seattle-based AI startup. We're launching an experiment to showcase what's possible with Fixie's real-time LLM-powered voice platform. You can check it out at <a href="https://hisanta.ai" rel="nofollow noreferrer">https://hisanta.ai</a> - you can have live voice chats with Santa, Mrs. Claus, Rudolph, and other friends (toggle the naughty/nice switch at the top for some other characters!)<p>We'd love to get your help testing this and get any feedback -- especially from people with kids :-)<p>All the code for this app is open source: <a href="https://github.com/fixie-ai/hisanta.ai">https://github.com/fixie-ai/hisanta.ai</a><p>This is not just a thin wrapper around LLMs. To get the performance to this level, we've had to do a lot of engineering to wire together ASR, LLMs, and TTS models efficiently, and are doing some clever things to hide latency. Happy to answer any questions about the technology.<p>The Fixie platform (<a href="https://fixie.ai" rel="nofollow noreferrer">https://fixie.ai</a>) powers the app and embeds the logic for managing voice sessions with LLM agents, which can be built either through a no-code UI or using our AI.JSX (<a href="https://ai-jsx.com" rel="nofollow noreferrer">https://ai-jsx.com</a>) framework for building LLM apps. We support a range of ASR and TTS models under the hood as well.<p>We'd love your feedback! Drop me a line or join our Discord: <a href="https://discord.com/invite/tRMV7PW8f2" rel="nofollow noreferrer">https://discord.com/invite/tRMV7PW8f2</a><p>Thanks!
Matt on behalf of the Fixie team