Tavus's banner
Tavus's profile picture

Tavus

@tavus • 43,309 subscribers

The human computing company.

Shorts

Today two new PALs just dropped. Meet Sophie and Ryan, joining Charlie, Noah, and Ashley as the newest AI companions. Each one has their own personality, their own opinions, and a memory that captures everything from your conversations the moment you start talking.

Today two new PALs just dropped. Meet Sophie and Ryan, joining Charlie, Noah, and Ashley as the newest AI companions. Each one has their own personality, their own opinions, and a memory that captures everything from your conversations the moment you start talking.

863,966 views

Introducing our new family of state-of-the-art AI models: Phoenix-3, Raven-0, and Sparrow-0. Together they bring Conversational Video Interfaces (CVI) to the next level, and power Charlie, our new demo persona 👋

Introducing our new family of state-of-the-art AI models: Phoenix-3, Raven-0, and Sparrow-0. Together they bring Conversational Video Interfaces (CVI) to the next level, and power Charlie, our new demo persona 👋

580,946 views

Something new is coming. Human computing. A shift in how we connect with AI... and who’s on the other side.

Something new is coming. Human computing. A shift in how we connect with AI... and who’s on the other side.

204,199 views

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

Introducing Griffin, the first model to pass the video Turing test. 48% of people who talked to it live thought it was a real human. Previous systems have had a pass rate <3%. It is #1 on NVIDIA's benchmark for full-duplex AI video. It’s the first Human Interaction Model (HIM).
1:48
tavus's profile picture

Introducing Griffin, the first model to pass the video Turing test. 48% of people who talked to it live thought it was a real human. Previous systems have had a pass rate <3%. It is #1 on NVIDIA's benchmark for full-duplex AI video. It’s the first Human Interaction Model (HIM).

Tavus

21,137,808 views • 17 days ago

Ari solves a Rubik's cube while Griffin coaches him from what it sees in his hands, and when he goes quiet to think, it waits. Its perception is always on, so it acts without being asked. Note: this actually blew our minds seeing happen live.
1:41
tavus's profile picture

Ari solves a Rubik's cube while Griffin coaches him from what it sees in his hands, and when he goes quiet to think, it waits. Its perception is always on, so it acts without being asked. Note: this actually blew our minds seeing happen live.

Tavus

1,044,243 views • 17 days ago

When machines meet us where we are and truly understand us, we unlock a future where using a machine will be as easy as talking to a friend or coworker. A tutor for every student that notices when they’re lost, an elderly care companion that listens, or the perfect assistant.
0:38
tavus's profile picture

When machines meet us where we are and truly understand us, we unlock a future where using a machine will be as easy as talking to a friend or coworker. A tutor for every student that notices when they’re lost, an elderly care companion that listens, or the perfect assistant.

Tavus

725,184 views • 17 days ago

Watch Brittney and Mars try to trip Griffin up at Simon Says. To play, it has to listen for "Simon says," watch their hands and move its own, all at the same time. It generates the whole frame, not just a face.
0:40
tavus's profile picture

Watch Brittney and Mars try to trip Griffin up at Simon Says. To play, it has to listen for "Simon says," watch their hands and move its own, all at the same time. It generates the whole frame, not just a face.

Tavus

448,951 views • 17 days ago

While Mars is still telling Griffin about a boring date, it laughs, nods and asks questions instead of waiting for her to stop. That's full duplex: listening, watching and talking at the same time, the way people actually talk.
0:55
tavus's profile picture

While Mars is still telling Griffin about a boring date, it laughs, nods and asks questions instead of waiting for her to stop. That's full duplex: listening, watching and talking at the same time, the way people actually talk.

Tavus

337,738 views • 17 days ago

Mid-story, Mars holds up a peacock, and Griffin seamlessly writes it into the plot. It sees while it speaks, so what it sees can change what it's saying. Show it something and it's part of the conversation.
1:17
tavus's profile picture

Mid-story, Mars holds up a peacock, and Griffin seamlessly writes it into the plot. It sees while it speaks, so what it sees can change what it's saying. Show it something and it's part of the conversation.

Tavus

306,810 views • 17 days ago

See how Sagar keeps his eyes on the soldering iron while Griffin talks him through the job and counts the seconds for him. Time is part of the conversation too, not just words. That's what a good coach does without being asked.
1:10
tavus's profile picture

See how Sagar keeps his eyes on the soldering iron while Griffin talks him through the job and counts the seconds for him. Time is part of the conversation too, not just words. That's what a good coach does without being asked.

Tavus

264,148 views • 17 days ago

Introducing Tavus PAL Maker. The first no-code way to build a PAL, a new kind of application that sees, hears, acts, remembers, and emotionally understands you like a friend or coworker, whether it's working with one person or a thousand. Anyone can now describe the PAL they imagine and watch it become real. A tutor that remembers you. A nurse that checks in after surgery. Someone who makes sure your grandmother is never lonely. All through a simple conversation.
1:20
tavus's profile picture

Introducing Tavus PAL Maker. The first no-code way to build a PAL, a new kind of application that sees, hears, acts, remembers, and emotionally understands you like a friend or coworker, whether it's working with one person or a thousand. Anyone can now describe the PAL they imagine and watch it become real. A tutor that remembers you. A nurse that checks in after surgery. Someone who makes sure your grandmother is never lonely. All through a simple conversation.

Tavus

1,267,126 views • 2 months 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
tavus's profile picture

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

2,088,596 views • 8 months ago

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
tavus's profile picture

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

1,672,977 views • 8 months ago

Introducing Phoenix-4.5, the fastest and most expressive real-time human rendering model on the market. More natural than ever before: richer facial animation, more expressive emotion and micro-movements, and movement that now extends through the upper body. It is the closest AI has ever come to passing the Turing test face to face.
5:17
tavus's profile picture

Introducing Phoenix-4.5, the fastest and most expressive real-time human rendering model on the market. More natural than ever before: richer facial animation, more expressive emotion and micro-movements, and movement that now extends through the upper body. It is the closest AI has ever come to passing the Turing test face to face.

Tavus

196,830 views • 1 month 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.
5:01
tavus's profile picture

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

103,057 views • 1 month ago

Introducing Tavus Magic Canvas. Now a PAL can bring anything to life inside a shared canvas at just the right time, a chart dynamically drawn from the numbers being discussed, a question answered on the spot, a calendar with times to pick, a field for the detail that must be exact. Turn it on for any PAL with a click.
0:58
tavus's profile picture

Introducing Tavus Magic Canvas. Now a PAL can bring anything to life inside a shared canvas at just the right time, a chart dynamically drawn from the numbers being discussed, a question answered on the spot, a calendar with times to pick, a field for the detail that must be exact. Turn it on for any PAL with a click.

Tavus

168,491 views • 3 months ago

Introducing Tavus Google Meet integration. Now a PAL can join a Google Meet, a real participant in the call you were already going to have, taking its turn the way any other guest would. Make and deploy a customized notetaker, personal assistant, or even a meeting host in a few clicks.
1:04
tavus's profile picture

Introducing Tavus Google Meet integration. Now a PAL can join a Google Meet, a real participant in the call you were already going to have, taking its turn the way any other guest would. Make and deploy a customized notetaker, personal assistant, or even a meeting host in a few clicks.

Tavus

163,944 views • 3 months ago

We're proud to support Elevare, who built an AI care companion for new moms that stays with them from pregnancy through their baby's first year. They partner with Tavus because real human connection happens face to face, and a new mom deserves that at any hour.
3:01
tavus's profile picture

We're proud to support Elevare, who built an AI care companion for new moms that stays with them from pregnancy through their baby's first year. They partner with Tavus because real human connection happens face to face, and a new mom deserves that at any hour.

Tavus

32,747 views • 19 days ago

Introducing Tavus Presentation Mode. Now a PAL can take you through a live presentation, walking your material from start to finish or going straight to the part a question calls for.
0:52
tavus's profile picture

Introducing Tavus Presentation Mode. Now a PAL can take you through a live presentation, walking your material from start to finish or going straight to the part a question calls for.

Tavus

94,616 views • 3 months ago

We just dropped a new SoTA lipsync model on @FAL: Hummingbird-0 Available now as a research preview, it's the most accurate zero-shot lipsync model we’ve tested, open or closed source.
0:45
tavus's profile picture

We just dropped a new SoTA lipsync model on @FAL: Hummingbird-0 Available now as a research preview, it's the most accurate zero-shot lipsync model we’ve tested, open or closed source.

Tavus

460,647 views • 1 year ago

A PAL no longer has to be human. Now with Phoenix-4.5, a single image is enough to turn a character into a PAL, whether anime, cartoon, or Pixar-style. It stays true to the original image, and it talks, listens, and moves in realtime like any other PAL.
0:35
tavus's profile picture

A PAL no longer has to be human. Now with Phoenix-4.5, a single image is enough to turn a character into a PAL, whether anime, cartoon, or Pixar-style. It stays true to the original image, and it talks, listens, and moves in realtime like any other PAL.

Tavus

18,895 views • 1 month ago

Interruptions are conversation killers. But how do you know when it's your turn to talk? (Hint: It's more than just waiting for silence). Our latest turn-taking model Sparrow-0 tackles exactly this. 🧵
0:58
tavus's profile picture

Interruptions are conversation killers. But how do you know when it's your turn to talk? (Hint: It's more than just waiting for silence). Our latest turn-taking model Sparrow-0 tackles exactly this. 🧵

Tavus

120,161 views • 1 year ago

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.
3:32
tavus's profile picture

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 • 9 months ago