Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

We’re thrilled to introduce the world’s fastest Conversational Video Interface for developers. Build rich, real-time video experiences with digital twins that can speak, see, and hear. ⏱️ Less than one second of latency 🤖 Realistic, intelligent digital twins 🔌 Plug and play end-to-end building blocks 🏷️ Fully white-labeled tech... show more

Tavus

10,485 subscribers

35,742 views • 2 years ago •via X (Twitter)

Education Health & Wellness Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

Happy2 years ago

‌‌‌‌Beautiful promotional video

Tavus2 years ago

Thank you, made by the talented @ChrisCoxCap6 @NebulaSocial

Chris TheAI MktgGuy2 years ago

Wow, this Conversational Video Interface is a game-changer! I can already imagine the endless possibilities for immersive experiences. Can't wait to dive deeper and explore the capabilities of Carter and the Phoenix model!

Tavus2 years ago

@theai_golfnut Thanks Chris, appreciate the kind words :)

High Alpha2 years ago

🤯

Pete XL Pizza2 years ago

Impressive! Wow!

Sam Waitathu2 years ago

no way, I have spent my afternoon looking for this exact thing

Tavus2 years ago

it's fate

Dennis2 years ago

@sequoia Congrats!

Tavus2 years ago

@sequoia tysm

Related Videos

Introducing Sparrow-1, a conversational-flow control model built for real-time conversational video that sets the benchmark for human-level conversational timing and understanding in real-time AI.

Introducing Sparrow-1, a conversational-flow control model built for real-time conversational video that sets the benchmark for human-level conversational timing and understanding in real-time AI.

Tavus

47,995 views • 7 months ago

Build a real-time AI Voice Agent that can actually sell. In less than 30 minutes, you'll learn how to build a sophisticated real-time voice sales agent that can have natural conversations with potential customers. Includes a full code notebook, recorded tutorial, and docs The stack: ⚡ fast inference 🎙 LiveKit for real-time audio/video infrastructure 🗣 realistic speech synthesis (STT/TTS)

Build a real-time AI Voice Agent that can actually sell. In less than 30 minutes, you'll learn how to build a sophisticated real-time voice sales agent that can have natural conversations with potential customers. Includes a full code notebook, recorded tutorial, and docs The stack: ⚡ fast inference 🎙 LiveKit for real-time audio/video infrastructure 🗣 realistic speech synthesis (STT/TTS)

Sarah Chieng

452,438 views • 11 months ago

It’s TIME to shoot a TIME Magazine–style cover 🎬 See who’s on the cover and what they’re talking about — brought to life with stunning realism. Every scene in this video is fully AI-generated with Akool, delivering cinematic, ultra-realistic visuals that look and feel like the real thing. Welcome to the future of storytelling.

It’s TIME to shoot a TIME Magazine–style cover 🎬 See who’s on the cover and what they’re talking about — brought to life with stunning realism. Every scene in this video is fully AI-generated with Akool, delivering cinematic, ultra-realistic visuals that look and feel like the real thing. Welcome to the future of storytelling.

Akool Inc

27,368 views • 8 months ago

Announcing LemonSlice x Agora You can now use LemonSlice avatars - the most advanced avatars in the world - directly within Agora. Agora powers ultra-low-latency voice, video, livestreaming, and human-to-AI experiences around the world. Their customers include Whatnot (#1 live selling platform in the US, incl. the MrBeast livestream) and talkspace (#1 rated online therapy with 1M+ users). Create interactive, face-to-face AI experiences that can see, speak, listen, and react in real time!

Announcing LemonSlice x Agora You can now use LemonSlice avatars - the most advanced avatars in the world - directly within Agora. Agora powers ultra-low-latency voice, video, livestreaming, and human-to-AI experiences around the world. Their customers include Whatnot (#1 live selling platform in the US, incl. the MrBeast livestream) and talkspace (#1 rated online therapy with 1M+ users). Create interactive, face-to-face AI experiences that can see, speak, listen, and react in real time!

LemonSlice

42,089 views • 21 days ago

Today we’re releasing Chroma 1.0 → the world first open-source, end-to-end, real-time speech-to-speech model → with personalized voice cloning Trained by FlashLabs. Deployed on FlashAI👉 An open research-grade alternative to the OpenAI Realtime model. Voice Test dubbing Elon Musk and Lex Fridman: 🔥What’s real (evals and benchmarks attached): ⚡ 2× faster than real-time ) 📘 SGLang Cookbook: 📄 Paper + benchmarks: 🤗 Models: 💻 Inference code: 🔁 RT if you believe real-time AI should be open 💬 Reply if you’re building on Conversational Voice AI products

Today we’re releasing Chroma 1.0 → the world first open-source, end-to-end, real-time speech-to-speech model → with personalized voice cloning Trained by FlashLabs. Deployed on FlashAI👉 An open research-grade alternative to the OpenAI Realtime model. Voice Test dubbing Elon Musk and Lex Fridman: 🔥What’s real (evals and benchmarks attached): ⚡ 2× faster than real-time ) 📘 SGLang Cookbook: 📄 Paper + benchmarks: 🤗 Models: 💻 Inference code: 🔁 RT if you believe real-time AI should be open 💬 Reply if you’re building on Conversational Voice AI products

FlashLabs

1,249,084 views • 7 months ago

⚽️ Athletes have millions of followers - but they’re not truly connected with them. Now the game changes. We’re helping athletes build real, transparent connections with their fans through technology. Starting with one of the world’s best players, our platform lets athletes launch their official digital cards - talent tokens - unlocking exclusive fan perks and access to unique football experiences on Solana. A new era of decentralized sport begins - built, live, and growing. Thanks to Jupiter (🐱, 🐐), Meteora, and Moonshot for their incredible support and tech. 🙌

⚽️ Athletes have millions of followers - but they’re not truly connected with them. Now the game changes. We’re helping athletes build real, transparent connections with their fans through technology. Starting with one of the world’s best players, our platform lets athletes launch their official digital cards - talent tokens - unlocking exclusive fan perks and access to unique football experiences on Solana. A new era of decentralized sport begins - built, live, and growing. Thanks to Jupiter (🐱, 🐐), Meteora, and Moonshot for their incredible support and tech. 🙌

Trendex | Official Talent Tokens

160,452 views • 10 months ago

Today, we're launching C1 by Thesys on Product Hunt and giving away up to 5M free tokens if you retweet this and sign up within 24 hours. C1 is the world’s first Generative UI API that augments LLMs to respond with interactive UI like charts, forms, cards, and more in real-time, instead of plain text. Integrates seamlessly with any LLM, framework or MCP in just 2 lines of code - Fully customisable to match your brand - Supports custom components - Renders instantly with no latency Ship rich, interactive AI apps 10× faster, with 80% less UI overhead.

Rabi Shanker Guha

71,837 views • 11 months ago

NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on Hugging Face 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This NVIDIA model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥

NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on Hugging Face 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This NVIDIA model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥

Chaz Wargnier ♨️

565,905 views • 7 months ago

Learn to build conversational AI voice agents in "Building AI Voice Agents for Production", created in collaboration with LiveKit and RealAvatar, and taught by dsa (Co-founder & CEO of LiveKit), Shayne (Developer Advocate, LiveKit), and Nedelina Teneva (Head of AI at RealAvatar, an AI Fund portfolio company). Voice agents combine speech and reasoning capabilities to enable real-time conversations. They're already being used to support customer service, to improve accessibility in healthcare, for entertainment applications, and for talk therapy. In this course, you’ll learn to build voice agents that listen, reason, and respond naturally. You’ll follow the architecture used to create the "AI Andrew" Avatar, a collaborative project between and RealAvatar that responds to users in what sounds like my voice. You’ll build a voice agent from scratch and deploy it to the cloud, enabling support for many simultaneous users. What you’ll learn: - Understand the fundamentals of voice agents, including key components like speech-to-text (STT), text-to-speech (TTS), and LLMs, and how latency is introduced at each layer. - Explore voice agent architectures and the trade-offs between modular pipelines and speech-to-speech APIs. - Explore how platforms like LiveKit mitigate latency issues with optimized networking infrastructure and low-latency communication protocols. - Learn how to connect client devices to voice agents using WebRTC—and why it outperforms HTTP and WebSocket for low-latency audio streaming. - Incorporate voice activity detection (VAD), end-of-turn detection, and context management to detect turns, handle interruptions, and manage conversational flow. - Understand the trade-offs between latency, quality, and cost in an example in which you build a voice agent and change its voice. - Equip your agent with metrics to measure latency at each stage of the voice pipeline and learn the key levers you can pull to make your agent faster and more responsive. The voice agents built in this course also incorporate voice technology from , a supporting contributor to the project. By the end of this course, you'll have learned the components of an AI voice agent pipeline, combined them into a system with low-latency communication, and deployed them on cloud infrastructure so it scales to many users. I’m looking forward to seeing what voice agents you build from this course! Please sign up here:

Andrew Ng

87,711 views • 1 year ago

I just had one of the most traumatising experiences of my life… Went into Tesco for some pork chops, and what do I find? HALAL sausages sitting in the pork section. I was shaken to my core. This is not just wrong, it’s inhumane. 😳🐖 And as if that wasn’t enough, guess what turned up at my house? A Digital ID straight from the Home Office. 👀 Check out the video to see it all (Digital ID reveal at the end).

Sensitive content

I just had one of the most traumatising experiences of my life… Went into Tesco for some pork chops, and what do I find? HALAL sausages sitting in the pork section. I was shaken to my core. This is not just wrong, it’s inhumane. 😳🐖 And as if that wasn’t enough, guess what turned up at my house? A Digital ID straight from the Home Office. 👀 Check out the video to see it all (Digital ID reveal at the end).

Sir Shoaib

395,748 views • 11 months ago

Today, we’re thrilled to announce the launch of Akool Live Camera — a breakthrough in real-time AI video generation and the newest innovation in our Akool Live Suite. This is more than a product launch — it's a new chapter in how we communicate, connect, and show up in the world. Akool Live Camera creates photorealistic, dynamic avatars that reflect your expressions, voice, gestures, and emotional tone — all in real time, in any language. Built for live interactions—not pre-recorded content—Akool Live Camera powers: 🌍 Live AI Video Translation – Speak in one language, appear fluent in another — lip-sync, voice, expressions & gestures included. 🎭 Live Face Swap – Keep your host’s identity consistent, even when they’re not live. 🧑‍💼 Real-Time AI Avatars – Branded, expressive avatars for privacy, support, and seamless comms. 💡 Real-Time Video Generation – Coming soon: speak your idea, and your video creates itself. In real time. This is the birth of a new category: Live AI Video Generation. This is live, unscripted, intelligent visual presence. 💡 Welcome to the future of video, where anyone, anywhere, can show up fully and authentically — in any language, at any time. 🔗 Get early access: 📣 Read the full announcement: #AkoolLiveCamera #AIvideo #LiveTranslation #AvatarTech #RealTimeVideo #RealTimeAI #GenerativeAI #SyntheticMedia #AIAvatars #LiveTranslation #FaceSwap #FutureOfVideo #AIInnovation #TechLaunch

Today, we’re thrilled to announce the launch of Akool Live Camera — a breakthrough in real-time AI video generation and the newest innovation in our Akool Live Suite. This is more than a product launch — it's a new chapter in how we communicate, connect, and show up in the world. Akool Live Camera creates photorealistic, dynamic avatars that reflect your expressions, voice, gestures, and emotional tone — all in real time, in any language. Built for live interactions—not pre-recorded content—Akool Live Camera powers: 🌍 Live AI Video Translation – Speak in one language, appear fluent in another — lip-sync, voice, expressions & gestures included. 🎭 Live Face Swap – Keep your host’s identity consistent, even when they’re not live. 🧑‍💼 Real-Time AI Avatars – Branded, expressive avatars for privacy, support, and seamless comms. 💡 Real-Time Video Generation – Coming soon: speak your idea, and your video creates itself. In real time. This is the birth of a new category: Live AI Video Generation. This is live, unscripted, intelligent visual presence. 💡 Welcome to the future of video, where anyone, anywhere, can show up fully and authentically — in any language, at any time. 🔗 Get early access: 📣 Read the full announcement: #AkoolLiveCamera #AIvideo #LiveTranslation #AvatarTech #RealTimeVideo #RealTimeAI #GenerativeAI #SyntheticMedia #AIAvatars #LiveTranslation #FaceSwap #FutureOfVideo #AIInnovation #TechLaunch

Akool Inc

6,175,751 views • 1 year ago

This isn’t a video. It’s a live, web-native prototype of work I designed for Trello. Real interface components. Real motion. Real interaction. It’s built in React and TypeScript—not rendered as a sequence of frames. I rebuilt the interface as live DOM so I could show the product work in motion, with panels, cards, and calendar elements layered independently in CSS 3D space. A custom browser timeline drives camera movement, rotation, depth, and pacing in real time, while responsive layouts and a Safari-optimized rendering path keep the experience smooth across devices. You can replay the sequence, switch views, and interact with selected parts of the interface directly on the page. It’s a front-end prototype, not a connected Trello product—but the interface, motion, and selected interactions are genuinely running in the browser. See it here: All built with OpenAI Developers Codex hosted on ChatGPT Sites.

This isn’t a video. It’s a live, web-native prototype of work I designed for Trello. Real interface components. Real motion. Real interaction. It’s built in React and TypeScript—not rendered as a sequence of frames. I rebuilt the interface as live DOM so I could show the product work in motion, with panels, cards, and calendar elements layered independently in CSS 3D space. A custom browser timeline drives camera movement, rotation, depth, and pacing in real time, while responsive layouts and a Safari-optimized rendering path keep the experience smooth across devices. You can replay the sequence, switch views, and interact with selected parts of the interface directly on the page. It’s a front-end prototype, not a connected Trello product—but the interface, motion, and selected interactions are genuinely running in the browser. See it here: All built with OpenAI Developers Codex hosted on ChatGPT Sites.

Levin Stanley

31,479 views • 2 days ago

Human conversation is one of the hardest problems in AI. Today, we're introducing Sparrow-2, our state-of-the-art, real-time conversational understanding model. It gives Tavus PALs something most voice AI still lacks: understanding what’s happening in a conversation and deciding what to do next- when to listen, wait, speak, or keep speaking.

Human conversation is one of the hardest problems in AI. Today, we're introducing Sparrow-2, our state-of-the-art, real-time conversational understanding model. It gives Tavus PALs something most voice AI still lacks: understanding what’s happening in a conversation and deciding what to do next- when to listen, wait, speak, or keep speaking.

Tavus

64,452 views • 7 days ago

This "AI Software Engineer" is doing something different to everyone else: Databutton specializes in building full-stack applications using React in the front end and Python in the back end. That's it. I think this gives them a huge advantage: They can fine-tune their models on a very focused tech stack and make them better than anyone else. Instead of having to worry about every programming language and tech stack out there, they specialize and make a much better experience. I think this is smart. In the attached video, I started building a landing page to sell a course. You can see in real time how everything works.

This "AI Software Engineer" is doing something different to everyone else: Databutton specializes in building full-stack applications using React in the front end and Python in the back end. That's it. I think this gives them a huge advantage: They can fine-tune their models on a very focused tech stack and make them better than anyone else. Instead of having to worry about every programming language and tech stack out there, they specialize and make a much better experience. I think this is smart. In the attached video, I started building a landing page to sell a course. You can see in real time how everything works.

Santiago

49,379 views • 1 year ago

"If you sign up for digital ID... you'll never be able to say no to the government again." British ex-MP Andrew Bridgen: "They can only implement all the aspects of Agenda 2030... if they have digital ID." "If we can stop digital ID, it's very, very difficult to see how we can end up with the dystopian future which I believe is in line for us." "Digital ID will be a massive tool of control. It'll always be sold to you as it's for your own convenience and for your own security, and there's an old saying that if you're ever willing to trade your freedom for security, you'll end up with neither freedom nor security." "We will be like prisoners out on license, where we're tagged and they'll know exactly where we are and what we're doing all the time." "That can't be allowed to happen." Credit: Andrew Bridgen Russell Brand

Wide Awake Media

167,763 views • 11 months ago

do you have an interesting yet simple idea that you can't get claude code / codex to build? if so, I want to hear it or see a sketch, and then try building a decent start for you. I need little distractions when I'm tired of working on my own projects that never end. the end result would be an open source code artifact, and I'll do my best to include prompts/process where possible. video is the quintessential example, time-helix built from a Tim Babb sketch/idea

do you have an interesting yet simple idea that you can't get claude code / codex to build? if so, I want to hear it or see a sketch, and then try building a decent start for you. I need little distractions when I'm tired of working on my own projects that never end. the end result would be an open source code artifact, and I'll do my best to include prompts/process where possible. video is the quintessential example, time-helix built from a Tim Babb sketch/idea

Codetaur

24,190 views • 4 months ago

🚨🚨Can agents earn money, run a business, or even self-organize a society in the physical social world? 🤖🤖 Can agents learn continually to survive and thrive in embodied environments, like how human babies grow? 👶 Super excited to introduce SimWorld, an open-ended simulator of LLM agents in infinite, realistic embodied worlds. SimWorld features 3 key designs: 1⃣Open-ended realistic world simulation - built on Unreal Engine 5, with accurate physical social dynamics - 100+ built-in environments (city, island, wilderness ...) - language-controllable procedural generation - text-to-3D asset generation 2⃣Native interface for LLM/VLM agents - Gym-like agent-environment interaction APIs - plug in any LLMs/VLMs (GPTs, Gemini, Qwen ...) - rich multi-modal perception - open-vocabulary natural-language action outputs 3⃣Diverse physical and social reasoning scenarios - long-horizon embodied reasoning - multi-agent collaboration / competition - easily customizable for any reasoning tasks SimWorld is fully open-sourced, with a hope to become a foundational infrastructure for real-world agent research across disciplines: robotics, economy, public health, education, etc. Project website + more details in the thread👇 ...1/

🚨🚨Can agents earn money, run a business, or even self-organize a society in the physical social world? 🤖🤖 Can agents learn continually to survive and thrive in embodied environments, like how human babies grow? 👶 Super excited to introduce SimWorld, an open-ended simulator of LLM agents in infinite, realistic embodied worlds. SimWorld features 3 key designs: 1⃣Open-ended realistic world simulation - built on Unreal Engine 5, with accurate physical social dynamics - 100+ built-in environments (city, island, wilderness ...) - language-controllable procedural generation - text-to-3D asset generation 2⃣Native interface for LLM/VLM agents - Gym-like agent-environment interaction APIs - plug in any LLMs/VLMs (GPTs, Gemini, Qwen ...) - rich multi-modal perception - open-vocabulary natural-language action outputs 3⃣Diverse physical and social reasoning scenarios - long-horizon embodied reasoning - multi-agent collaboration / competition - easily customizable for any reasoning tasks SimWorld is fully open-sourced, with a hope to become a foundational infrastructure for real-world agent research across disciplines: robotics, economy, public health, education, etc. Project website + more details in the thread👇 ...1/

Lianhui Qin

65,156 views • 9 months ago

We're changing our name. Captions is now Mirage. Today's most popular medium is short-form video. It's the fastest-growing format, it’s what people want, and it’s what brands need to grow. But unlike other forms of AI content like text or image, which can be generated and ready-to-use with a single prompt, generated video still requires a lot of manual work and editing to be ready to share. This is where the real opportunity lies. The way we see it, the real race for AI video hasn’t even begun. The world is waiting for a foundation model for video that can take an idea and produce a fully usable, cohesive output from scratch. So that’s what we’re building. We’re rebranding to Mirage to reflect our expanded vision for video, starting with the short-form format, through frontier AI research and models. Check it out at mirage dot app

We're changing our name. Captions is now Mirage. Today's most popular medium is short-form video. It's the fastest-growing format, it’s what people want, and it’s what brands need to grow. But unlike other forms of AI content like text or image, which can be generated and ready-to-use with a single prompt, generated video still requires a lot of manual work and editing to be ready to share. This is where the real opportunity lies. The way we see it, the real race for AI video hasn’t even begun. The world is waiting for a foundation model for video that can take an idea and produce a fully usable, cohesive output from scratch. So that’s what we’re building. We’re rebranding to Mirage to reflect our expanded vision for video, starting with the short-form format, through frontier AI research and models. Check it out at mirage dot app

Gaurav Misra

137,517 views • 1 year ago