Loading video...

Video Failed to Load

Go Home

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's profile picture

Tavus

9,680 subscribers

47,879 views • 5 months ago •via X (Twitter)

EducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Most conversational AI understands words, not people. Introducing Raven-1, our audio and video perception model that gives AI the ability to understand emotion, intent, and context the way humans do.
4:50

Most conversational AI understands words, not people. Introducing Raven-1, our audio and video perception model that gives AI the ability to understand emotion, intent, and context the way humans do.

Tavus

1,672,443 views • 4 months ago

Introducing — a new conversational Voice AI platform and API for creating human-like voice agents and voice interfaces. Powered by our new Large Dialogue Model (LDM), Play LDM 1.0 makes the speech generation contextual; handles turn-taking, interruption, voice energy and emotion modulation for a natural, fluid, human conversations in real-time.
2:02

Introducing — a new conversational Voice AI platform and API for creating human-like voice agents and voice interfaces. Powered by our new Large Dialogue Model (LDM), Play LDM 1.0 makes the speech generation contextual; handles turn-taking, interruption, voice energy and emotion modulation for a natural, fluid, human conversations in real-time.

PlayAI

105,616 views • 2 years ago

Introducing Phoenix-4, the most advanced real-time human rendering model ever built. Its the first real-time model to render every pixel at runtime, generate and control emotional states, listen actively, and actually behave the way humans do in conversation.
5:08

Introducing Phoenix-4, the most advanced real-time human rendering model ever built. Its the first real-time model to render every pixel at runtime, generate and control emotional states, listen actively, and actually behave the way humans do in conversation.

Tavus

2,086,309 views • 3 months ago

I built an AI that can schedule meetings for me through ElevenLabs Conversational AI and Cal.com
2:30

I built an AI that can schedule meetings for me through ElevenLabs Conversational AI and Cal.com

ElevenLabs Developers

13,924 views • 1 year ago

Conversational AI makes building voice agents easier than ever before. Make a Conversational Agent for your business in seconds, with
0:28

Conversational AI makes building voice agents easier than ever before. Make a Conversational Agent for your business in seconds, with

ElevenLabs Developers

18,645 views • 10 months ago

Introducing AI Voice + 3D in real-time. 🥕 Integrate with OpenAI Real-time API ✨ Create conversational AI experiences 🌳 Drive states, variables, morph targets 🍓 Trigger events and actions from instructions Make your own AI Voice 3D experiences with Spline.
1:08

Introducing AI Voice + 3D in real-time. 🥕 Integrate with OpenAI Real-time API ✨ Create conversational AI experiences 🌳 Drive states, variables, morph targets 🍓 Trigger events and actions from instructions Make your own AI Voice 3D experiences with Spline.

Spline

105,825 views • 1 year ago

We've added native, low-latency RAG to Conversational AI — enabling your voice agents to access and use large knowledge bases in real time.
5:49

We've added native, low-latency RAG to Conversational AI — enabling your voice agents to access and use large knowledge bases in real time.

ElevenLabs

23,107 views • 1 year ago

Introducing the ElevenLabs React Native SDK Build cross-platform conversational AI agents for iOS and Android in minutes. WebRTC and first-class Expo support built in. Docs links below:
0:31

Introducing the ElevenLabs React Native SDK Build cross-platform conversational AI agents for iOS and Android in minutes. WebRTC and first-class Expo support built in. Docs links below:

ElevenLabs Developers

75,946 views • 10 months ago

What if xAI's Grok had a voice? 👀 Using the new ElevenLabs Conversational AI SDK + Replit ⠕ agent, I built a real-time chatbot that you can speak to powered by Grok all in under 15 minutes! Demo and code below.
1:16

What if xAI's Grok had a voice? 👀 Using the new ElevenLabs Conversational AI SDK + Replit ⠕ agent, I built a real-time chatbot that you can speak to powered by Grok all in under 15 minutes! Demo and code below.

Ammaar Reshi

117,276 views • 1 year ago

$Lexi AI Fam, Our bot upgrades are now live with enhanced conversational AI features! What is Conversational AI? Conversational AI refers to technologies that enable machines to interact with humans in a natural, human-like manner. This includes understanding and processing natural language, enabling more fluid and intuitive interactions. New Features - Token Trading: Trade tokens by simply typing out the token contract and amount. No need for a fixed syntax! - Multilingual Support: You can now use any language to trade tokens. Check out the attached video demonstrating these new capabilities.
1:14

$Lexi AI Fam, Our bot upgrades are now live with enhanced conversational AI features! What is Conversational AI? Conversational AI refers to technologies that enable machines to interact with humans in a natural, human-like manner. This includes understanding and processing natural language, enabling more fluid and intuitive interactions. New Features - Token Trading: Trade tokens by simply typing out the token contract and amount. No need for a fixed syntax! - Multilingual Support: You can now use any language to trade tokens. Check out the attached video demonstrating these new capabilities.

Lexi AI

140,043 views • 1 year ago

The NFL Combine just got an AI upgrade. Used during the 2025 event, a real-time conversational assistant —built with Azure AI Foundry and SOUTHWORKS—delivered instant insights to help scouts and coaches make faster and smarter decisions.
1:46

The NFL Combine just got an AI upgrade. Used during the 2025 event, a real-time conversational assistant —built with Azure AI Foundry and SOUTHWORKS—delivered instant insights to help scouts and coaches make faster and smarter decisions.

Microsoft

41,094 views • 1 year ago

🚨 BREAKING: NVIDIA just removed the biggest friction point in Voice AI They open-sourced PersonaPlex 7B, a real-time conversational model. It listens and speaks simultaneously to handle natural interruptions and overlaps. 100% Open Source.
0:43

🚨 BREAKING: NVIDIA just removed the biggest friction point in Voice AI They open-sourced PersonaPlex 7B, a real-time conversational model. It listens and speaks simultaneously to handle natural interruptions and overlaps. 100% Open Source.

How To Prompt

699,834 views • 2 months ago

NVIDIA just removed the biggest friction point in Voice AI 🤯 They've open-sourced PersonaPlex-7B, a full-duplex conversational model that can listen and speak at the same time. Instead of waiting for you to finish talking, it uses a dual-stream architecture to process and respond in real-time. 100% Open-Source and Free.
0:42

NVIDIA just removed the biggest friction point in Voice AI 🤯 They've open-sourced PersonaPlex-7B, a full-duplex conversational model that can listen and speak at the same time. Instead of waiting for you to finish talking, it uses a dual-stream architecture to process and respond in real-time. 100% Open-Source and Free.

Simplifying AI

278,640 views • 4 months ago

Moss (Moss (YC F25)) is the real-time semantic search for conversational AI. By bringing retrieval latency under 10 ms, Moss makes AI conversations feel natural, as fluid and instant as talking to a human. Congrats on the launch, Sri Malireddi & Harsha Nalluru!
1:17

Moss (Moss (YC F25)) is the real-time semantic search for conversational AI. By bringing retrieval latency under 10 ms, Moss makes AI conversations feel natural, as fluid and instant as talking to a human. Congrats on the launch, Sri Malireddi & Harsha Nalluru!

Y Combinator

26,597 views • 7 months ago

This human conversational AI from sesame freaked me out.
1:53

This human conversational AI from sesame freaked me out.

Marouane Lamharzi Alaoui

23,532 views • 1 year ago

Warmcore Tech is a Taiwan-based AI robotics company specializing in humanoid AI companion robots that combine emotional intelligence, realistic bionic design, and real-time conversational capabilities. At least that’s their cover story. 😂
0:48

Warmcore Tech is a Taiwan-based AI robotics company specializing in humanoid AI companion robots that combine emotional intelligence, realistic bionic design, and real-time conversational capabilities. At least that’s their cover story. 😂

Champagne Joshi

15,911 views • 2 months ago

.Marc Benioff on customer service digital agents: AI agents operate at a higher level than chatbots, conversational and human-like. #DF24
0:59

.Marc Benioff on customer service digital agents: AI agents operate at a higher level than chatbots, conversational and human-like. #DF24

Vala Afshar

20,488 views • 1 year ago

Continuing with the 3D Conversational Lab, now implementing real-time lip-sync for both the user's audio & the AI agents I'm processing the Gemini Live API native audio to make the synchronization immediate Check out the flow. Inspiration explained below...
0:27

Continuing with the 3D Conversational Lab, now implementing real-time lip-sync for both the user's audio & the AI agents I'm processing the Gemini Live API native audio to make the synchronization immediate Check out the flow. Inspiration explained below...

Arturo Paracuellos

18,570 views • 4 months ago

Introducing Lightning V3 - it beats every model we tested against. ElevenLabs, Cartesia, OpenAI. Lightning sets a new SOTA with V3 in conversational text-to-speech. → Highest MOS score for conversational TTS at 3.9 → ~76% win rate vs gpt-4o-mini-tts on naturalness → 15 languages with mid-sentence code-switching → Built from scratch for voice agents, not read-aloud Every TTS model sounds clean in a demo. You type a sentence and you get beautiful audio. Voice agents don't work that way. They stream. They're generating audio in real-time chunks with half the context missing. That's where everything breaks. A great reading voice and a great conversational voice are fundamentally different things. A conversational voice has to sound like it's thinking - with the pauses, the rhythm shifts, the reactions. It has to handle the way real people actually talk, including switching languages mid-sentence. That's what V3 does. V3.1 also ships voice cloning. 5 to 15 seconds of audio, no fine-tuning, production-grade clone across 15 languages. Blog link in the comments.
1:33

Introducing Lightning V3 - it beats every model we tested against. ElevenLabs, Cartesia, OpenAI. Lightning sets a new SOTA with V3 in conversational text-to-speech. → Highest MOS score for conversational TTS at 3.9 → ~76% win rate vs gpt-4o-mini-tts on naturalness → 15 languages with mid-sentence code-switching → Built from scratch for voice agents, not read-aloud Every TTS model sounds clean in a demo. You type a sentence and you get beautiful audio. Voice agents don't work that way. They stream. They're generating audio in real-time chunks with half the context missing. That's where everything breaks. A great reading voice and a great conversational voice are fundamentally different things. A conversational voice has to sound like it's thinking - with the pauses, the rhythm shifts, the reactions. It has to handle the way real people actually talk, including switching languages mid-sentence. That's what V3 does. V3.1 also ships voice cloning. 5 to 15 seconds of audio, no fine-tuning, production-grade clone across 15 languages. Blog link in the comments.

Sudarshan Kamath

71,172 views • 2 months ago