[HN Gopher] Show HN: Sparrow-1 - Audio-native model for human-le...
___________________________________________________________________
Show HN: Sparrow-1 - Audio-native model for human-level turn-taking
without ASR
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...
Author : code_brian
Score : 112 points
Date : 2026-01-14 18:01 UTC (1 days ago)
(HTM) web link (www.tavus.io)
(TXT) w3m dump (www.tavus.io)
| orliesaurus wrote:
| 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.
| qfavret wrote:
| try signing up for the API platform on the site. You can access
| it there
| nubg wrote:
| Any examples available? Sounds amazing.
| bpanahij wrote:
| 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 wrote:
| > 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 wrote:
| 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 wrote:
| 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 wrote:
| 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 wrote:
| 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.
| fudged71 wrote:
| Different industry, but our marketing guy once said "You know
| what this [perfect] metric means? We can never use it in
| marketing because it's not believable"
| khalic wrote:
| Just include some noise, it's like the most available
| resource in the universe
| drob518 wrote:
| Never thought of noise as a resource, but yea.
| bpanahij wrote:
| 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 wrote:
| 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 wrote:
| > perfectly willing
|
| dreaming
| bpanahij wrote:
| 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.
| ttul wrote:
| 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.
| mavamaarten wrote:
| Agreed. English is not my native language. And I do speak it
| well, it's just that sometimes I need a second to think mid-
| sentence. None of the live chat models out there handle this
| well. Claude just starts answering before I've even had the
| chance to finish a sentence.
| Tostino wrote:
| English _is_ my native language, and I still have this
| problem all the time with voice models.
| sigmoid10 wrote:
| Anthropic doesn't have any realtime multimodal audio models
| available, they just use STT and TTS models slapped on top of
| Claude. So they are currently the worst provider if you
| actually want to use voice communication.
| code_brian wrote:
| It's unfortunate though, because Anthropic LLMs and ecosystem
| is the best IMHO. Tavus (we) and Anthropic should form a
| partnership.
| MrDunham wrote:
| 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.
| code_brian wrote:
| 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.
| butlike wrote:
| Am I not allowed to cut you off if you're ramble-y and
| incoherent?
| BizarroLand wrote:
| Its rude if you're a human, and entirely unacceptable if you
| are a computer.
| code_brian wrote:
| 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.
| BizarroLand wrote:
| That's an interesting way to think about it, I like that.
|
| It also implies that being the person who has something
| to say but is unable to get into the conversation due to
| following the conversational semantics is akin to going
| to a dance in your nice clothes but not being able to
| find a dance partner.
| Taikonerd wrote:
| 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 wrote:
| Metric | Sparrow-1 Precision 100% Recall 100%
|
| Common ...
| reubenmorais wrote:
| If you watch the demo video you can see how they would get
| this: the model is not aggressive enough. While it doesn't cut
| you off, which is nice, it also always waits an uncanny amount
| of time to chime in.
| oersted wrote:
| That should lead to a low recall: too many false negatives. I
| wonder how they are calculating it.
| bpanahij wrote:
| 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 wrote:
| Such things were doing a good-enough job scamming the elderly as
| it is--even with the silence-based delays.
| bpanahij wrote:
| 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 wrote:
| How do I try the demo for Sparrow-1? What is pricing like?
| bpanahij wrote:
| You can try Sparrow-1 with any of our PALs, or by signing up
| for a developer account.
| ljoshua wrote:
| 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.
| code_brian wrote:
| 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
| allan_s wrote:
| How does it compare with
| https://github.com/KoljaB/RealtimeVoiceChat , which is absent of
| the benchmark ?
| bpanahij wrote:
| I haven't tried that one yet, I'll check it out.
| sippeangelo wrote:
| That's not a turn-taking model, it's just a silence detection
| Python script based on whatever text comes out of Whisper...
| nubg wrote:
| 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.
| bpanahij wrote:
| 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.
| vpribish wrote:
| What is "ASR" - automatic speech recognition?
___________________________________________________________________
(page generated 2026-01-15 23:01 UTC)