HN Explorer

Show HN: Sparrow-1 – Audio-native model for human-level turn-taking without ASR (tavus.io)

123 points by code_brian ↗ HN
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

- Human-timed responses without silence-based delays

- Zero interruptions at sub-100ms median latency

- In benchmarks Sparrow-1 beats all existing models at real world turn-taking baselines

I wrote more about the work here: https://www.tavus.io/post/sparrow-1-human-level-conversation...

28 comments

[ 2.5 ms ] story [ 48.3 ms ] thread
orliesaurus
Literally no way to sign up to try. Put my email and password and it puts me into some wait list despite the video saying I could try the model today. That's what makes me mad about these kind of releases is that the marketing and the product don't talk together.
nubg
Any examples available? Sounds amazing.
bpanahij
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.
nextaccountic
> Non-verbal cues are invisible to text: Transcription-based models discard sighs, throat-clearing, hesitation sounds, and other non-verbal vocalizations that carry critical conversational-flow information. Sparrow-1 hears what ASR ignores.

Could Sparrow instead be used to produce high quality transcription that incorporate non-verbal cues?

Or even, use Sparrow AND another existing transcription/ASR thing to augment the transcription with non-verbal cues

bpanahij
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.
randyburden
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.
bpanahij
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.
dfajgljsldkjag
I am always skeptical of benchmarks that show perfect scores, especially when they come from the company selling the product. It feels like everyone claims to have solved conversational timing these days. I guess we will see if it is actually any good.
bpanahij
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.
cuuupid
The first time I met Tavus, their engineers (incl Brian!) were perfectly willing to sit down and build their own better Infiniband to get more juice out of H100s. There is pretty much nobody working on latency and realtime at the level they are, Sparrow-1 would be an defining achievement for most startups but will just be one of dozens for Tavus :)
lostmsu
> perfectly willing

dreaming

ttul
I tried talking to Claude today. What a nightmare. It constantly interrupts you. I don’t mind if Claude wants to spend ten seconds thinking about its reply, but at least let ME finish my thought. Without decent turn-taking, the AI seems impolite and it’s just an icky experience. I hope tech like this gets widely distributed soon because there are so many situations in which I would love to talk with a model. If only it worked.
MrDunham
I love Anthropic's models but their realtime voice is absolutely terrible. Every time I use it there is at least once that I curse at it for interrupting me.

My main use case for OpenAI/ChatGPT at this point is realtime voice chats.

OpenAI has done a pretty great job w/ realtime (their realtime API is pretty fantastic out of the box... not perfect, but pretty fantastic and dead simple setup). I can have what feels like a legitimate conversation with AI and it's downright magical feeling.

That said, the output is created by OpenAI models so it's... not my favorite.

I sometimes use ChatGPT realtime to think through/work through a problem/idea, have it create a detailed summary, then upload that summary to Claude to let 4.5 Opus rewrite/audit and come up with a better final output.

butlike
Am I not allowed to cut you off if you're ramble-y and incoherent?
Taikonerd
Agreed. I tried using Gemini's voice interface in their app. It went like this:

===

ME: "OK, so, I have a question about the economics of medicine. Uh..." [pauses to gather thoughts to ask question]

GEMINI: "Sure! Medical economics is the field of..."

===

And it's aggravated by the fact that all the LLMs love to give you page-long responses before it's your turn to talk again!

mentalgear
Metric | Sparrow-1 Precision 100% Recall 100%

Common ...

bpanahij
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.

krautburglar
Such things were doing a good-enough job scamming the elderly as it is--even with the silence-based delays.
bpanahij
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.
sourcetms
How do I try the demo for Sparrow-1? What is pricing like?
bpanahij
You can try Sparrow-1 with any of our PALs, or by signing up for a developer account.
ljoshua
Hey @code_brian, would Tavus make the conversational audio model available outside of the PALs and video models? Seems like this could be a great use case for voice-only agents as well.
nubg
Btw while I think this is cool and useful for real time voice interfaces for the general populace, I wonder if for professional users (eg a dev coding by dictating all day), a simple push to talk is not always going to be superior, because you can make long pauses while you think about something, this would creep out a human, but the AI would wait patiently for your push to talk.
vpribish
What is "ASR" - automatic speech recognition?
code_brian
Ah good question: Yes, ASR stands for Automatic Speech Recognition.
pugio
It sounds really cool, but I don't see any way of trying the model directly. I don't actually want a "Persona" or "Replica" - I just want to use the sparrow-one model. Is there any way to just make API calls to that model directly?