Conversational Replicas by Tavus
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 listening to humans talking and trying to really understand how people know when to talk, when to listen, and when to wait. I’ve also been hunting down failure modes of the current SoTA models. And while…
Conversational Replicas by Tavus launched on August 15, 2024 with 694 votes, #28 of 5,471 launches that month and more than 99% of that year's launches. The site was still online in September 2026, 2 years on.
In plain words
Conversational Replicas by Tavus is a platform for developers to build real-time video conversations with digital twins that can speak, see, and hear. The system processes interactions with less than a second of latency, creating a complete conversational pipeline. It's designed for developers who want to integrate lifelike digital characters into applications, with video streaming and AI capabilities powering the interactions.
written from the facts on this page · September 2026
From the sources
With CVI, developers can now build live video conversations with digital twins – that actually feel real. It's the only end-to-end conversational pipeline with less than a second of latency. Check out a live demo on our website www.tavus.io ✨
Sparrow-2 is a real-time conversational understanding model that jointly models turn-taking, interruptions, backchannels, and the full acoustic scene as a single, unified system. It is an audio-native, streaming-first engine, rebuilt from the ground up, that goes beyond endpoint detection to transform the entire audio stream into decisions about when to listen, wait, or speak at a native 10 ms fra
Choose how you want to experience Tavus. Whether you’re building with our APIs or meeting a PAL, you can switch anytime. Build real-time, human-like AI experiences using Tavus APIs and tools. Best for developers, founders, and teams integrating Tavus into a product. Meet your personal AI companions who listen, remember, and are always present. Best for individuals looking to talk, explore, and connect with a friend. [ This is a research and technical overview of Sparrow-2 . To jump to what the model unlocks, click here ] Human conversation relies on a largely subconscious understanding of speaker intent, prosody, and the acoustic environment. We continuously interpret what another person is…from tavus.io
In the maker’s words, at launch
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…
Does a similar job
all alternatives →- ARA real time AI video agent with under 1 second of latency2024 · ▲455
Hey it’s Hassaan & Quinn – co-founders of Tavus, an AI research company and developer platform for video APIs. We’ve been building AI video models for ‘digital twins’ or ‘avatars’ since 2020. We’re sharing some of the challenges we faced building an AI video interface that has realistic conversations with a human, including getting it to under 1 second of latency. To try it, talk to Hassaan’s digital twin: https://www.hassaanraza.com, or to our "demo twin" Carter: https://www.tavus.io We built this because until now, we've had to adapt communication to the limits of…
Conversational AI 2.0 From ElevenLabs2025 · elevenlabs.io · ▲652Luke from ElevenLabs here. We just released Scribe Realtime v2, our new real-time Speech to Text model. We rebuilt it from the ground up around a new architecture that uses predictive transcription – it anticipates the next likely word before it’s spoken. That makes it both fast (around 150 ms latency) and highly accurate. Scribe v2 Realtime outperforms every low latency transcription model across 30 commonly used EU and Asian languages – 93.5% accuracy, compared to Gemini 2.5 Flash (91.4%), GPT-4o MiniTranscribe (90.7%), and Deepgram Nova 3 (85%). It supports 90+ languages including…
I built a sub-500ms latency voice agent from scratchMar 2026 · ntik.me · ▲570I built a voice agent from scratch that averages ~400ms end-to-end latency (phone stop → first syllable). That’s with full STT → LLM → TTS in the loop, clean barge-ins, and no precomputed responses. What moved the needle: Voice is a turn-taking problem, not a transcription problem. VAD alone fails; you need semantic end-of-turn detection. The system reduces to one loop: speaking vs listening. The two transitions - cancel instantly on barge-in, respond instantly on end-of-turn - define the experience. STT → LLM → TTS must stream. Sequential pipelines are dead on arrival for natural…
An open source framework for voice assistants2024 · github.com · ▲346I've been obsessed for the past ~year with the possibilities of talking to LLMs. I built a bunch of one-off prototypes, shared code on X, started a Meetup group in SF, and co-hosted a big hackathon. It turns out that there are a few low-level problems that everybody building conversational/real-time AI needs to solve on the way to building/shipping something that works well: low-latency media transport, echo cancellation, voice activity detection, phrase endpointing, pipelining data between models/services, handling voice interruptions, swapping out different…
- S2Sparrow-2 – Noise cancellation isn't designed for conversational AISep 2026 · sparrow2.tavuslabs.org · ▲11
Have a real conversation with a Tavus PAL and watch Sparrow-2 read it live: who holds the floor, who is acknowledging, and who just cut in.
- IBI built a non-linear UI for ChatGPT2024 · grafychat.com · ▲459
Hi HN, I built this out of frustration of the evergrowing list of AI models and features to try and to fit my workflow. The visual approach clicks for me so i went with it, it provides more freedom and control of the outcome, because predictable results and increased productivity is what I’m after when using conversational AI. The app is packed with features, my most used are prompt library, voice input and text search, narration is useful too. The app is local-first and works right in the browser, no sign up needed and it's absolutely free to try. BYOAK – bring your own API Keys. Let me…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Product Hunt launch ↗ · launch text quoted in part
Launched alongside, August 2024
the whole month →
Jupitrr AI▲1,195Jupitrr AI turns raw talking videos into scroll-stopping content for coaches and consultants. Research, script, record, edit, and publish in one app.
AI · 2024 · jupitrr.com
Hey there HN! We’re Joe and Stopa, and today we’re open sourcing InstantDB, a client-side database that makes it easy to build real-time and collaborative apps like Notion and Figma. Building modern apps these days involves a lot of schleps. For a basic CRUD app you need to spin up servers, wire up endpoints, integrate auth, add permissions, and then marshal data from the backend to the frontend and back again. If you want to deliver a buttery smooth user experience, you’ll need to add optimistic updates and rollbacks. We do these steps over and over for every feature we build, which can…
Dev tools · 2024 · github.com