News for hackers. Stuff that matters.

A comment on Show HN: Sparrow-1 – Audio-native model for human-level turn-taking without ASR.

Re:Show HN: Sparrow-1 – Audio-native model for human-level t... by randyburden on Thursday January 15, 2026 @01:11AM (#46628697)
Awesome. We've been using Sparrow-0 in our platform since launch, and I'm excited to move to Sparrow-1 over the next few days. Our training and interview pre-screening products rely heavily on Tavus's AI avatars, and this upgrade (based on the video in your blog post) looks like it addresses some real pain points we've run into. Really nice work.
[ Parent | on HN ]
Re:Show HN: Sparrow-1 – Audio-native model for human-level t... by bpanahij on Thursday January 15, 2026 @11:50AM (#46635362)
That’s great! I also built Sparrow-0, and Sparrow-1 was designed to address Sparrow-0’s shortcomings. 1 is a much better model, both in terms of responsiveness and patience.
[ Parent | on HN ]