bpanahij - Hackdot

Re:Show HN: Sparrow-1 – Audio-native model for human-level turn-taking... on Thursday January 15, 2026 @12:10PM (#46635725)

That’s unfortunate and certainly not what I spend my time dreaming about. My favorite use case for the elderly is as a sort of companion for sharing their story for future generations. One of our partners uses our technology to help elderly. But yeah, this kind of technology makes AI feel more natural, so we should be aware of that and make sure it’s used for good.

Re:Show HN: Sparrow-1 – Audio-native model for human-level turn-taking... on Thursday January 15, 2026 @12:08PM (#46635684)

The response timing in the chart in the blog post shows that even with perfect precision/recall Sparrow-1 also has the fastest true positive response times.

The turn taking models were evaluated in a controlled environment with no additional cascaded steps: LLM, TTS, Phx. This matters to get apples to apples comparison: without the rest of the pipeline variability influencing the measurements.

The video conversation examples are sparrow-1 within the full pipeline. These responses aren’t as fast as sparrow itself because the LLM, TTS, facial rendering, and network transport also take time. Without Sparrow-1 they would be slower. Sparrow-1 enables the responses being as fast as they are, and with a faster CVI pipeline configuration the responses can be as fast as 430ms in my testing.

Re:Show HN: Sparrow-1 – Audio-native model for human-level turn-taking... on Thursday January 15, 2026 @12:00PM (#46635545)

You can try Sparrow-1 with any of our PALs, or by signing up for a developer account.

Re:Show HN: Sparrow-1 – Audio-native model for human-level turn-taking... on Thursday January 15, 2026 @11:59AM (#46635535)

Try out the PALs: they all use Sparrow-1. You can try Charlie on Tavus.io on the homepage in one of the retro retro-styled windows there.

Re:Show HN: Sparrow-1 – Audio-native model for human-level turn-taking... on Thursday January 15, 2026 @11:58AM (#46635503)

This is a very good idea. We currently have a model in our perception system (Raven-1) that performs this partially. It uses audio to understand tone and augment the transcription we send to the conversational LLM. That seems to have an impact on the conversational style of the replicas output, in a good way. We’re still evaluating that model and will post updates when we have better insights.

Re:Show HN: Sparrow-1 – Audio-native model for human-level turn-taking... on Thursday January 15, 2026 @11:54AM (#46635444)

You should be skeptical, and try it out. I selected 28 long conversations for our evaluation set, all unseen audio. Every turn taking model makes tradeoffs, and I tried to make the best tradeoffs for each model by adjusting and tuning the implementations. I’m certainly not in a position as the creator of Sparrow to be totally objective. However we did use unaltered real conversational audio to evaluate. I tried to find examples that would challenge Sparrow-1 with lots of variation in speaker style across the conversations.

Re:Show HN: Sparrow-1 – Audio-native model for human-level turn-taking... 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.

Re:Show HN: Sparrow-1 – Audio-native model for human-level turn-taking... on Thursday January 15, 2026 @11:48AM (#46635328)

I haven’t tried that one yet, I’ll check it out.

Re:Show HN: Sparrow-1 – Audio-native model for human-level turn-taking... on Thursday January 15, 2026 @11:46AM (#46635303)

Maybe infiniband is a bit more than we can handle. That technology is incredible! You are right though, we have been willing to build things we needed that didn’t exist yet, or were not fast enough or natural enough. Sparrow-1, Raven-1, and Phoenix-4 are all examples that, and we have more on the way.

Re:Show HN: Sparrow-1 – Audio-native model for human-level turn-taking... on Thursday January 15, 2026 @11:42AM (#46635231)

As a dev myself, I see a couple of modes of operation: - push to talk - long form conversation - short form conversation

In both conversational approaches the AI can respond with simple acknowledgements. When prompted by the user the AI could go into longer discussions and explanations.

It might be nice for the AI to quickly confirm it hears me and for it to give me subtle queues that it’s listening: backchannels: “yeah”, and non-verbal: “mhmm”. So I can imagine having a developer assistant that feels more like working with another dev than working with a computer.

That being said, there is room for all modes, all at the same time, and at different times shifting between them. A lot of time I just don’t want to talk at all.

Re:Show HN: A real time AI video agent with under 1 second of latency on Tuesday October 01, 2024 @03:51PM (#41713359)

Thanks for checking it out!

Re:Show HN: A real time AI video agent with under 1 second of latency on Tuesday October 01, 2024 @03:48PM (#41713316)

https://www.tavus.io/pricing

Scroll down the page to find our pricing.

Re:Show HN: A real time AI video agent with under 1 second of latency on Tuesday October 01, 2024 @03:46PM (#41713306)

You could hack this together now with OBS and Tavus.

Re:Show HN: A real time AI video agent with under 1 second of latency on Tuesday October 01, 2024 @03:21PM (#41713006)

Thanks for these thoughts and compliments. I love the idea of preventing landfill with this tech. Our team is awesome and we really love our customers and all the jobs that can be done with this kind of tech!

Re:Show HN: A real time AI video agent with under 1 second of latency on Tuesday October 01, 2024 @02:36PM (#41712383)

We're partnering with GPU infrastructure providers like Replicate. In addition, we have done some engineering to bring down our stack's cold and warm boot times. With sufficient caches on disk, and potentially a running process/memory snapshot we can bring these cold/warm boot times down to under 5 seconds. Of course, we're making progress every week on this, and it's getting better all the time.

Re:Show HN: A real time AI video agent with under 1 second of latency on Tuesday October 01, 2024 @02:33PM (#41712349)

Scroll down the page and the per minute pricing is there: https://www.tavus.io/pricing

We bill in 6 second increments, so you only pay for what you use in 6 second bins.

Re:Show HN: A real time AI video agent with under 1 second of latency on Tuesday October 01, 2024 @02:30PM (#41712282)

We have the ability to send phonetic pronunciations as guidance, and this could be a great addition to our LLM/response generation stack! Adding a check for names and then adding in the phoneme.

Re:Show HN: A real time AI video agent with under 1 second of latency on Tuesday October 01, 2024 @01:44PM (#41711681)

Thanks for that insight. Brian here, one of the engineers for CVI. I've spoken with CVI so much, and as it has become more natural, I've found myself becoming more comfortable with a conversational style of interaction with the vastness of information contained within the LLMs and context under the hood. Whereas, with Google or other search based interactions I'm more point and shoot. I find CVI is more of an experience and for me yields more insight.

Re:Show HN: Infinity – Realistic AI characters that can speak on Sunday September 08, 2024 @12:34AM (#41478225)

Checkout Tavus.io for realtime. They have a great API for realtime conversational replicas. You can configure the CVI to do just about anything you want to do with a realtime streaming replica.

Re:Show HN: Infinity – Realistic AI characters that can speak on Saturday September 07, 2024 @11:44PM (#41478061)

Tavus.io already does this. They have realtime conversational replicas: with a < 1 second response time. Hyper realistic too.