code_brian

code_brian on Hacker News

Re:Show HN: Sparrow-2 – Noise cancellation isn't designed for conversa... on Tuesday September 08, 2026 @08:40PM (#49619217)

Thank you.

Re:Show HN: Sparrow-2 – Noise cancellation isn't designed for conversa... on Tuesday September 08, 2026 @08:39PM (#49619215)

Thanks, as a builder and a craftsman, I really appreciate that.

Re:Show HN: Sparrow-2 – Solving the cocktail party problem on Tuesday September 08, 2026 @03:28PM (#49615607)

Thank you for trying it out, and I'm so pleased that it is working for you. I've had such an improvement in my outcomes on conversations with sparrow-two.

Show HN: Sparrow-2 – Noise cancellation isn't designed for conversational AI

Posted by code_brian on Tuesday September 08, 2026 @12:16PM
from the show-hn dept.

https://sparrow2.tavuslabs.org/

Hey there, I’m Brian. I've been shipping conversational models at Tavus for the past two years. I want to tell you about our latest audio-understanding/turn-taking model: Sparrow-2! It’s a new category of model and a unique new approach to conversational flow understanding.Earlier this year we launched Sparrow-1, (at the time) our SoTA turn-taking model. Since our Sparrow-1 launch, I’ve spent a...

( Read More... | 5 comments | 10 points | on HN )

Show HN: Sparrow-2 – Solving the cocktail party problem

Posted by code_brian on Thursday August 27, 2026 @01:52PM
from the show-hn dept.

https://www.tavus.io/blog/sparrow-2

Hey there, I’m Brian. I've been shipping conversational models over here at Tavus for the past two years. I want to tell you about our new audio-understanding model: Sparrow-2! It’s a new category of model and a unique new approach to conversational audio.Earlier this year we launched Sparrow-1, (at the time) our SoTA turn taking model. Since our Sparrow-1 launch, I’ve spent a lot of time...

( Read More... | 2 comments | 6 points | on HN )

Re:Show HN: Sparrow-1 – Audio-native model for human-level turn-taking... on Thursday January 15, 2026 @08:25PM (#46641884)

Yeah, I can relate to that. Maybe it's also because you are too shy to ask someone to dance. I think I learned that lesson: just ask, and be unafraid to fail. Things tend to work themselves out. Much of this is experimentation. I think our models need to be open to that: which is one cool thing about Sparrow-1: it's a meta-in-context learner. This means that when it try's and fails, or you try and fail, it learns at runtime to adapt.

Re:Show HN: Sparrow-1 – Audio-native model for human-level turn-taking... on Thursday January 15, 2026 @08:22PM (#46641864)

Ah good question: Yes, ASR stands for Automatic Speech Recognition.

Re:Show HN: Sparrow-1 – Audio-native model for human-level turn-taking... on Thursday January 15, 2026 @02:59PM (#46638309)

It's unfortunate though, because Anthropic LLMs and ecosystem is the best IMHO. Tavus (we) and Anthropic should form a partnership.

Re:Show HN: Sparrow-1 – Audio-native model for human-level turn-taking... on Thursday January 15, 2026 @02:58PM (#46638290)

You can reach out to our sales team. You can chat with our AI SDR here, and they will review it and reach out. https://www.tavus.io/demo

Re:Show HN: Sparrow-1 – Audio-native model for human-level turn-taking... on Thursday January 15, 2026 @02:10PM (#46637543)

The one thing that really surprised me, the thing I learned that's affected my conversational abilities the most: turn taking in conversation is a negotiation: there are no set rules. There are protocols: - bids - holds / stays - implications (semantic / prosodic)

But then the actual flow of the conversation is deeply semantic in the best conversations, and the rules are very much a "dance" or a negotiation between partners.

Re:Show HN: Sparrow-1 – Audio-native model for human-level turn-taking... on Thursday January 15, 2026 @02:07PM (#46637506)

I use Claude Code for everything, and I love Anthropic's models. I don't know why, but it wasn't until reading this that I realized: I can use Sparrow-1 with Anthropic's models within CVI. Adding this to my todo list.

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

Posted by code_brian on Wednesday January 14, 2026 @01:01PM
from the show-hn dept.

https://www.tavus.io/post/sparrow-1-human-level-conversational-timing-in-real-time-voice

For the past year I've been working to rethink how AI manages timing in conversation at Tavus. I've spent a lot of time listening to conversations. Today we're announcing the release of Sparrow-1, the most advanced conversational flow model in the world.Some technical details: - Predicts conversational floor ownership, not speech endpoints - Audio-native streaming model, no ASR dependency -...

( Read More... | 49 comments | 4 points | on HN )