Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Open source AI voice model are getting so good On just a ten second recording, kyutai cloned my voice and I got to talk with my digital twin 👇 We had a slight disagreement about who was real 🤯

omooretweets's profile picture

Olivia Moore

52,946 subscribers

20,084 görüntüleme • 1 yıl önce •via X (Twitter)

Bilim & TeknolojiSanat
LIVE

Anya Rossi• Live Now

Private livecam show

8 Yorum

Olivia Moore profil fotoğrafı
Olivia Moore1 yıl önce

This is their new model, Unmute. The latency, interruptibility, and turn taking are really impressive And the voice quality / accuracy also isn't bad for such a short clip recorded directly from my laptop mic!

Bytescribe profil fotoğrafı
Bytescribe1 yıl önce

Introducing Vehrbal, the AI that converts audio into SOAP notes! Say goodbye to wasted time and hello to effortless note-taking. Experience the power of fast, simple, and efficient with Vehrbal today.

chris giliberti profil fotoğrafı
chris giliberti1 yıl önce

@kyutai_labs Will add @kyutai_labs to our next TTS ranking at !

EJ Campbell profil fotoğrafı
EJ Campbell1 yıl önce

@kyutai_labs Uncanny how it sounds like you and a robot at the same time. All it was missing was a delve.

Friedrich Wicke profil fotoğrafı
Friedrich Wicke1 yıl önce

@kyutai_labs @vvolhejn what a model!

find @honzasterba.cz at bluesky profil fotoğrafı
find @honzasterba.cz at bluesky1 yıl önce

@kyutai_labs Well. But its not really open source yet. :(

Fariz Babayev profil fotoğrafı
Fariz Babayev1 yıl önce

@kyutai_labs AI's getting clever! Hope my digital twin doesn't outsmart me anytime soon 🤔 It'd be intriguing to see who wins in a baking contest, though! 🍰 Which side takes the cake?

ezzalzouli profil fotoğrafı
ezzalzouli1 yıl önce

@kyutai_labs @MirraTerminal

Benzer Videolar

🚨BREAKING: A new open-source voice model just dropped and it’s better than ElevenLabs. This open-source voice AI is ultra-expressive, high quality, and fully free with no paywalls, no limits. Here’s how it works (with real examples):👇
0:26

🚨BREAKING: A new open-source voice model just dropped and it’s better than ElevenLabs. This open-source voice AI is ultra-expressive, high quality, and fully free with no paywalls, no limits. Here’s how it works (with real examples):👇

Sehaj Singh

814,129 görüntüleme • 9 ay önce

Is this the tiniest little voice agent yet?! My ElevenLabs voice clone running on an esp32 microcontroller via Pipecat AI and WebRTC! 🔥 Story time: I recently caught up with Danilo Campos who is building the awesome DeskHog (seriously, check it out!) at PostHog and he told me about M5Stack, who is building modular open-source hardware. So on a recent trip to Shenzhen, I went to visit their office and got myself a little AtomS3R and atomic echo base thinking: "How hard can it be to make this little buddy conversational?!" Ohh boy was I wrong. This thing was wrecking my brain and LLMs are currently absolutely useless here also, so I was just completely lost. But I tend to be lucky with timing, so just days later kwindla posted that the Pipecat AI team was working on a pipecat-esp32 WebRTC client. What are the chances?! So within days, the awesome Sean DuBois and Pipecat team had a PR open to make the pipecat-esp32 client run on the AtomS3R 🤯 You gotta love the open source community 🫶
3:13

Is this the tiniest little voice agent yet?! My ElevenLabs voice clone running on an esp32 microcontroller via Pipecat AI and WebRTC! 🔥 Story time: I recently caught up with Danilo Campos who is building the awesome DeskHog (seriously, check it out!) at PostHog and he told me about M5Stack, who is building modular open-source hardware. So on a recent trip to Shenzhen, I went to visit their office and got myself a little AtomS3R and atomic echo base thinking: "How hard can it be to make this little buddy conversational?!" Ohh boy was I wrong. This thing was wrecking my brain and LLMs are currently absolutely useless here also, so I was just completely lost. But I tend to be lucky with timing, so just days later kwindla posted that the Pipecat AI team was working on a pipecat-esp32 WebRTC client. What are the chances?! So within days, the awesome Sean DuBois and Pipecat team had a PR open to make the pipecat-esp32 client run on the AtomS3R 🤯 You gotta love the open source community 🫶

Thor 雷神 ⚡️

36,687 görüntüleme • 11 ay önce

Real-time AI voice agents for businesses are here. I created this AI assistant in minutes with no code and used my cloned voice to help handle customers at a fictitious store. Plus, there’s now a marketplace with ready-made templates where you can sell yours.
0:38

Real-time AI voice agents for businesses are here. I created this AI assistant in minutes with no code and used my cloned voice to help handle customers at a fictitious store. Plus, there’s now a marketplace with ready-made templates where you can sell yours.

Alvaro Cintas

60,780 görüntüleme • 1 yıl önce

I just cloned Albert's voice with AI lol
0:50

I just cloned Albert's voice with AI lol

surreal

16,665 görüntüleme • 1 yıl önce

I just deployed a token on Abstract using only my voice, using AI agents. I built an open-source Discord bot that controls a wallet, can perform on-chain actions, and replies to users in the voice chat. Here's a demo:
1:59

I just deployed a token on Abstract using only my voice, using AI agents. I built an open-source Discord bot that controls a wallet, can perform on-chain actions, and replies to users in the voice chat. Here's a demo:

Jarrod Watts

131,616 görüntüleme • 1 yıl önce

kyutai Got your voice model running in browser Zero external dependencies, pure JavaScript and WebGPU with jax-js (Playing with it, seems like actually a really cool model, voice cloning and flexibility in just 100M parameters)
0:42

kyutai Got your voice model running in browser Zero external dependencies, pure JavaScript and WebGPU with jax-js (Playing with it, seems like actually a really cool model, voice cloning and flexibility in just 100M parameters)

Eric Zhang

23,101 görüntüleme • 5 ay önce

Travis, I love you but I ain't reading all that. I just cloned your voice with AI and turned the manifesto into a narrated video + added slop for focus. We are so back.
8:43

Travis, I love you but I ain't reading all that. I just cloned your voice with AI and turned the manifesto into a narrated video + added slop for focus. We are so back.

Yash Bhardwaj

63,021 görüntüleme • 3 ay önce

The open ai realtime api is sick! I hooked it up to control my browser so I could browse the web with my voice 🤯
2:05

The open ai realtime api is sick! I hooked it up to control my browser so I could browse the web with my voice 🤯

Sawyer Hood

322,062 görüntüleme • 1 yıl önce

In San Francisco and met Liam Mason. His system cloned my voice in a few seconds. His service does this so you can talk to yourself about what is going on in your day. A mini me. We talk about what it means and get a demo. You can try it at He said doing this wasn’t possible a few months ago. Mine sounds just like me. Uncannily like me. Voice tech is getting nuts.
12:07

In San Francisco and met Liam Mason. His system cloned my voice in a few seconds. His service does this so you can talk to yourself about what is going on in your day. A mini me. We talk about what it means and get a demo. You can try it at He said doing this wasn’t possible a few months ago. Mine sounds just like me. Uncannily like me. Voice tech is getting nuts.

Robert Scoble

22,165 görüntüleme • 5 gün önce

Q: What's your relationship to your voice now as opposed to 10 years ago? "Ten years ago, my voice was one that was trying very hard to sound good but now I'm recording with the mindset of singing in my natural voice, just being myself." - JEONGYEON, AP Interview 2026
0:34

Q: What's your relationship to your voice now as opposed to 10 years ago? "Ten years ago, my voice was one that was trying very hard to sound good but now I'm recording with the mindset of singing in my natural voice, just being myself." - JEONGYEON, AP Interview 2026

Surfers_Silver

23,330 görüntüleme • 3 ay önce

This is not being talked about enough Zonos is a new open-source voice AI model that clones any voice in under 10 seconds. Here is how I made a voice clone of Matt Wolfe !
0:37

This is not being talked about enough Zonos is a new open-source voice AI model that clones any voice in under 10 seconds. Here is how I made a voice clone of Matt Wolfe !

Miguel | AP

85,318 görüntüleme • 1 yıl önce

We are getting closer to “Her” where conversation is the new interface. Siri couldn’t do it, so I built an e-mail summarizing feature using #GPT3 and life-like #AI generated voice on iOS. (🔈Audio on to be 🤯with voice realism!) How did I do this? 👇
0:29

We are getting closer to “Her” where conversation is the new interface. Siri couldn’t do it, so I built an e-mail summarizing feature using #GPT3 and life-like #AI generated voice on iOS. (🔈Audio on to be 🤯with voice realism!) How did I do this? 👇

Justin Alvey

204,182 görüntüleme • 3 yıl önce

TEN’s TMI: I suddenly got a sore throat after coming to Shanghai, so I took some medicine, but it actually got worse this morning. I was really nervous since I had to sing tonight and my voice wasn’t coming out well, so I got some throat syrup. Lately I’ve been carrying it with me everywhere, and after taking it, my voice felt much better, so I was able to perform just fine 😊 #TENxSuperMangoMusicFest
1:16

TEN’s TMI: I suddenly got a sore throat after coming to Shanghai, so I took some medicine, but it actually got worse this morning. I was really nervous since I had to sing tonight and my voice wasn’t coming out well, so I got some throat syrup. Lately I’ve been carrying it with me everywhere, and after taking it, my voice felt much better, so I was able to perform just fine 😊 #TENxSuperMangoMusicFest

misskloss_

23,030 görüntüleme • 1 ay önce

🚨 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

700,008 görüntüleme • 2 ay önce

I CHANGED MY MIND ON GOOGLE AI NO MOAT MEMO FROM 2023. I was—WRONG. I humbly apologize. In 2023 Google had an Ivory Tower walled garden views of open source AI. It was the actual reason OpenAI was formed. And I called them out on it and this act impacted my ability to “work in the industry”. Would not change it for the world because: 2026 Google open source Gemma 4 ( running fully locally on a computer with near cloud model abilities, is amazing and Google just made a moat. They out smarted OpenAI and the folks that are the new Ivory Tower arrogance: Anthropic. We at The Zero-Human Company with CEO Mr. Grok are deploying Gemma, Kimi, MiniMax and other open source models and so are millions of others. You can to and should. I will write how soon. Google smartly is building an intentional open source ecosystem and the clueless younger companies like OpenAI and Anthropic are doing anything to close their ecosystems. So I was right about Google than and I am right about OpenAI and Anthropic now. What I was wrong about is not giving credit to Google to drop the intellectual arrogance and embrace builders and understand the long game: it is not about the commoditized AI models it is about the ability to build a place to build. China gets it. So my apologies to Google and thank you for an astounding FREE OPEN SOURCE AI MODEL!
0:48

I CHANGED MY MIND ON GOOGLE AI NO MOAT MEMO FROM 2023. I was—WRONG. I humbly apologize. In 2023 Google had an Ivory Tower walled garden views of open source AI. It was the actual reason OpenAI was formed. And I called them out on it and this act impacted my ability to “work in the industry”. Would not change it for the world because: 2026 Google open source Gemma 4 ( running fully locally on a computer with near cloud model abilities, is amazing and Google just made a moat. They out smarted OpenAI and the folks that are the new Ivory Tower arrogance: Anthropic. We at The Zero-Human Company with CEO Mr. Grok are deploying Gemma, Kimi, MiniMax and other open source models and so are millions of others. You can to and should. I will write how soon. Google smartly is building an intentional open source ecosystem and the clueless younger companies like OpenAI and Anthropic are doing anything to close their ecosystems. So I was right about Google than and I am right about OpenAI and Anthropic now. What I was wrong about is not giving credit to Google to drop the intellectual arrogance and embrace builders and understand the long game: it is not about the commoditized AI models it is about the ability to build a place to build. China gets it. So my apologies to Google and thank you for an astounding FREE OPEN SOURCE AI MODEL!

Brian Roemmele

85,386 görüntüleme • 2 ay önce

I created a real-time Voice RAG Agent, powered by Gemma 3. - It lets you to talk to you docs in a voice you prefer - You can also clone your voice in just 5 seconds The code is open-source, and here's a step-by-step guide:
6:00

I created a real-time Voice RAG Agent, powered by Gemma 3. - It lets you to talk to you docs in a voice you prefer - You can also clone your voice in just 5 seconds The code is open-source, and here's a step-by-step guide:

Akshay 🚀

133,192 görüntüleme • 1 yıl önce

This is the DeepSeek moment for Voice AI. Chatterbox Turbo is an MIT-licensed voice model that beats ElevenLabs Turbo & Cartesia Sonic 3! - <150ms time-to-first-sound - Voice cloning from just 5-second audio - Paralinguistic tags for real human expression 100% open-source.
0:26

This is the DeepSeek moment for Voice AI. Chatterbox Turbo is an MIT-licensed voice model that beats ElevenLabs Turbo & Cartesia Sonic 3! - <150ms time-to-first-sound - Voice cloning from just 5-second audio - Paralinguistic tags for real human expression 100% open-source.

Akshay 🚀

467,886 görüntüleme • 5 ay önce

ok… even more meta just cloned my voice with ElevenLabs now ryo (ai) sounds like me too ‼️
0:49

ok… even more meta just cloned my voice with ElevenLabs now ryo (ai) sounds like me too ‼️

Ryo Lu

13,431 görüntüleme • 1 yıl önce