Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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)

ekzhang1's profile picture

Eric Zhang

21,340 subscribers

23,101 Aufrufe • vor 5 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

This is the most realistic voice cloning I’ve seen. It doesn’t just copy the voice — it captures tone, rhythm, and emotion. Built with Hume’s EVI 3 speech-to-speech model and it even works with external LLMs like Groq, Anthropic, and DeepSeek. Just listen to this Ricky Gervais voice clone — same voice, same feeling 🎧 Try talking to the clone yourself →
0:39

This is the most realistic voice cloning I’ve seen. It doesn’t just copy the voice — it captures tone, rhythm, and emotion. Built with Hume’s EVI 3 speech-to-speech model and it even works with external LLMs like Groq, Anthropic, and DeepSeek. Just listen to this Ricky Gervais voice clone — same voice, same feeling 🎧 Try talking to the clone yourself →

Arsalan

26,923 Aufrufe • vor 11 Monaten

NEW: Kokoro v1.0 - 82M parameters, Apache 2.0 Licensed, multilingual TTS model - powered by WebGPU in browser! 🔥 Fully offline, 100% local with support for English, Spanish, French, Italian, Japanese and Mandarin! ⚡ Works directly in your browser with blazingly fast inference backed by ONNXRuntimeWeb npm i kokoro-js is all you need! What are you waiting for? try it out today! 🤗
0:56

NEW: Kokoro v1.0 - 82M parameters, Apache 2.0 Licensed, multilingual TTS model - powered by WebGPU in browser! 🔥 Fully offline, 100% local with support for English, Spanish, French, Italian, Japanese and Mandarin! ⚡ Works directly in your browser with blazingly fast inference backed by ONNXRuntimeWeb npm i kokoro-js is all you need! What are you waiting for? try it out today! 🤗

Vaibhav (VB) Srivastav

88,293 Aufrufe • vor 1 Jahr

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 🤯
0:27

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 🤯

Olivia Moore

20,084 Aufrufe • vor 1 Jahr

We’re excited to introduce Pocket TTS: a 100M-parameter text-to-speech model with high-quality voice cloning that runs on your laptop—no GPU required. Open-source, lightweight, and incredibly fast. 🧵👇
1:44

We’re excited to introduce Pocket TTS: a 100M-parameter text-to-speech model with high-quality voice cloning that runs on your laptop—no GPU required. Open-source, lightweight, and incredibly fast. 🧵👇

kyutai

236,570 Aufrufe • vor 5 Monaten

Presenting MetaVoice-1B, a 1.2B parameter base model for TTS (text-to-speech). * Emotional speech in English * Voice cloning with fine-tuning * Zero-shot cloning for American & British voices * Support for long-form synthesis
1:54

Presenting MetaVoice-1B, a 1.2B parameter base model for TTS (text-to-speech). * Emotional speech in English * Voice cloning with fine-tuning * Zero-shot cloning for American & British voices * Support for long-form synthesis

MetaVoice

111,799 Aufrufe • vor 2 Jahren

Introducing Voxtral WebGPU: Real-time speech transcription entirely in your browser. This demo runs Voxtral-Mini-4B, a powerful streaming ASR model from Mistral AI, locally on WebGPU. The model supports 13 languages and is capable of <500 ms latency. Fully private. Zero cost.
0:39

Introducing Voxtral WebGPU: Real-time speech transcription entirely in your browser. This demo runs Voxtral-Mini-4B, a powerful streaming ASR model from Mistral AI, locally on WebGPU. The model supports 13 languages and is capable of <500 ms latency. Fully private. Zero cost.

Xenova

94,356 Aufrufe • vor 3 Monaten

WebGPU is INSANE! 🤯 Here's a 24B parameter model running locally in a web browser, at a blazing ~50 tokens/second on my M4 Max. ⚡️ It's the largest model we've ever run with Transformers.js... and we're not stopping here. Big announcement soon.
1:05

WebGPU is INSANE! 🤯 Here's a 24B parameter model running locally in a web browser, at a blazing ~50 tokens/second on my M4 Max. ⚡️ It's the largest model we've ever run with Transformers.js... and we're not stopping here. Big announcement soon.

Xenova

36,159 Aufrufe • vor 3 Monaten

Your AI agent just got a voice. And yeah, it might be yours Goose + ElevenLabs = - Voice cloning - Audio editing - Speech transcription All from one single prompt.
0:44

Your AI agent just got a voice. And yeah, it might be yours Goose + ElevenLabs = - Voice cloning - Audio editing - Speech transcription All from one single prompt.

goose

93,245 Aufrufe • vor 1 Jahr

This is wild. Hume AI just announced a new AI voice model. It’s like ChatGPT Advanced Voice Mode, Elevenlabs Voice Design, and Google NotebookLM in one. t can create a voice with a whole personality from a description or 5 second clip. And more. 8 wild examples:
1:25

This is wild. Hume AI just announced a new AI voice model. It’s like ChatGPT Advanced Voice Mode, Elevenlabs Voice Design, and Google NotebookLM in one. t can create a voice with a whole personality from a description or 5 second clip. And more. 8 wild examples:

Min Choi

533,611 Aufrufe • vor 1 Jahr

Introducing Unbound: The first AI model with no guardrails that runs on your device - Browser, iPhone and Android Zero servers Zero cloud Zero deployment The whole model lives on your phone
0:33

Introducing Unbound: The first AI model with no guardrails that runs on your device - Browser, iPhone and Android Zero servers Zero cloud Zero deployment The whole model lives on your phone

EVAL Engine

16,455 Aufrufe • vor 1 Monat

say hello to my little friend 🤖 3D model control (move, rotate, scale, animate) using hand gestures and voice commands, running in real-time in the browser! created with Three.js, Rosebud AI, mediapipe computer vision, and web speech API credit to Quaternius for the robot model 🔗 demo below
0:52

say hello to my little friend 🤖 3D model control (move, rotate, scale, animate) using hand gestures and voice commands, running in real-time in the browser! created with Three.js, Rosebud AI, mediapipe computer vision, and web speech API credit to Quaternius for the robot model 🔗 demo below

AA

30,775 Aufrufe • vor 1 Jahr

💪🏻 This is SO COOL I build an app to count dumbbell reps with an AI model in the browser using Tensorflow.js and a pose detection model
0:54

💪🏻 This is SO COOL I build an app to count dumbbell reps with an AI model in the browser using Tensorflow.js and a pose detection model

Wes Bos

4,937,895 Aufrufe • vor 1 Jahr

Voice workflows just got stronger with gpt-realtime-1.5 in the Realtime API. The model offers more reliable instruction following, tool calling, and multilingual accuracy. Demo with Charlie Guo
1:46

Voice workflows just got stronger with gpt-realtime-1.5 in the Realtime API. The model offers more reliable instruction following, tool calling, and multilingual accuracy. Demo with Charlie Guo

OpenAI Developers

417,428 Aufrufe • vor 4 Monaten

made an interactive video model trained on tap-conditioned data.. tap the screen and it generates the next frames in realtime (small enough to run in the browser with webgpu, even on iphone)
0:24

made an interactive video model trained on tap-conditioned data.. tap the screen and it generates the next frames in realtime (small enough to run in the browser with webgpu, even on iphone)

sahir

23,151 Aufrufe • vor 2 Monaten

Smol TTS keeps getting better! Introducing OuteTTS v0.2 - 500M parameters, multilingual with voice cloning! 🔥 > Multilingual - English, Chinese, Korean & Japanese > Cross platform inference w/ llama.cpp > Zero-shot voice cloning > Trained on 5 Billion audio tokens > Qwen 2.5 0.5B LLM backbone > Trained via HF GPU grants Model weights on the hub, you can even run this on a Raspberry Pi! Go run, inference now! 🐐
0:50

Smol TTS keeps getting better! Introducing OuteTTS v0.2 - 500M parameters, multilingual with voice cloning! 🔥 > Multilingual - English, Chinese, Korean & Japanese > Cross platform inference w/ llama.cpp > Zero-shot voice cloning > Trained on 5 Billion audio tokens > Qwen 2.5 0.5B LLM backbone > Trained via HF GPU grants Model weights on the hub, you can even run this on a Raspberry Pi! Go run, inference now! 🐐

Vaibhav (VB) Srivastav

44,653 Aufrufe • vor 1 Jahr

Introducing Voice Cloning on Hedra! Record a quick clip, and we’ll clone your voice to bring your Hedra characters to life. Just upload or generate an image, and let your character speak in your voice. Try it for yourself! (Available to paid users only)
0:24

Introducing Voice Cloning on Hedra! Record a quick clip, and we’ll clone your voice to bring your Hedra characters to life. Just upload or generate an image, and let your character speak in your voice. Try it for yourself! (Available to paid users only)

Hedra

39,119 Aufrufe • vor 1 Jahr

Announcing the new SotA voice-cloning TTS model: 𝗩𝗼𝗶𝗰𝗲𝗦𝘁𝗮𝗿 ⭐️ VoiceStar is - autoregressive, - voice-cloning, - robust, - duration controllable, - *test-time extrapolation*, generates speech longer than training duration! Code&amp;Model:
0:41

Announcing the new SotA voice-cloning TTS model: 𝗩𝗼𝗶𝗰𝗲𝗦𝘁𝗮𝗿 ⭐️ VoiceStar is - autoregressive, - voice-cloning, - robust, - duration controllable, - *test-time extrapolation*, generates speech longer than training duration! Code&amp;Model:

Puyuan Peng

27,872 Aufrufe • vor 1 Jahr

Most AI agents force you into a new browser. Meet Composite, it isn't just a hosted browser session in the cloud, or a completely separate browser. Composite actually does the clicking, typing, and navigation inside your real tabs, in your existing browser. - Uses your existing browser, so there’s no migration, you keep your bookmarks, extensions, workflows - No lock-in. It works with any site, any AI model, you’re in control. - Composite does the clicks, types, and navigation for you. In your tabs. No migration. No lock-in. No learning curve. Download and start now:
0:39

Most AI agents force you into a new browser. Meet Composite, it isn't just a hosted browser session in the cloud, or a completely separate browser. Composite actually does the clicking, typing, and navigation inside your real tabs, in your existing browser. - Uses your existing browser, so there’s no migration, you keep your bookmarks, extensions, workflows - No lock-in. It works with any site, any AI model, you’re in control. - Composite does the clicks, types, and navigation for you. In your tabs. No migration. No lock-in. No learning curve. Download and start now:

The AI Colony

48,585 Aufrufe • vor 11 Monaten

Behold... GPT-OSS (20B) running 100% locally in your browser on WebGPU. This shouldn't be possible — but with Transformers.js v4 and ONNX Runtime Web, it is! A new class of AI apps is emerging. Zero-install, infinite distribution. Simply visit a website and run models locally.
1:23

Behold... GPT-OSS (20B) running 100% locally in your browser on WebGPU. This shouldn't be possible — but with Transformers.js v4 and ONNX Runtime Web, it is! A new class of AI apps is emerging. Zero-install, infinite distribution. Simply visit a website and run models locally.

Xenova

311,512 Aufrufe • vor 4 Monaten