Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

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

20,699 subscribers

94,623 Aufrufe • vor 6 Monaten •via X (Twitter)

Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

28 Kommentare

Profilbild von Xenova

Xenovavor 6 Monaten

Powered by 🤗 Transformers.js v4 (preview). I'm excited to see what the community builds with it! Try it out yourself! Demo + source code 👇

Profilbild von Vlad

Vladvor 6 Monaten

@MistralAI this is fire, it switches languages just like that. Awesome!

Profilbild von Xenova

Xenovavor 6 Monaten

@MistralAI Thanks! 🙏 I know right, the model is super impressive!

Profilbild von Vlad

Vladvor 6 Monaten

@MistralAI You have no idea how pump I am 😂 I feel like i have to add this somewhere to any of my free apps. 😂 Man the change from spanish to english and english to spanish right on the spot it's really insane.

Profilbild von DrFlask

DrFlaskvor 6 Monaten

@MistralAI

Profilbild von Xenova

Xenovavor 6 Monaten

@MistralAI Which OS/browser are you running? We recommend Chrome (or a Chromium-based browser), and most of our tests are on Mac/Windows.

Profilbild von DrFlask

DrFlaskvor 6 Monaten

@MistralAI it could be that the lack of a standard graphics architecture on linux makes webgpu harder.

Profilbild von matt palmer

matt palmervor 6 Monaten

@MistralAI lets goooo!

Profilbild von Xenova

Xenovavor 6 Monaten

@MistralAI You called it 😂

Profilbild von matt palmer

matt palmervor 6 Monaten

@MistralAI been following you long enough to know excited to build with this!

Profilbild von Haydon Ryan 🇦🇺🇺🇸

Haydon Ryan 🇦🇺🇺🇸vor 6 Monaten

@MistralAI It’s good. Been running voxtral mini for a while with

Profilbild von Cesar Bonadio

Cesar Bonadiovor 6 Monaten

@MistralAI Wohh, this is so good. It was able to correctly transcribe the name of my street, which is an Indigenous word in Portuguese. Congratulation!

Profilbild von 岡田泰彦｜光邦｜AI×印刷エヴァンジェリスト

岡田泰彦｜光邦｜AI×印刷エヴァンジェリストvor 6 Monaten

@MistralAI I feel we're getting closer and closer to a world where advanced voice AI is readily available to everyone. 高度な音声AIが誰にでもすぐ使える世界に、どんどん近づいていると感じます。

Profilbild von GPUBenchTest.com

GPUBenchTest.comvor 6 Monaten

@MistralAI Cannot wait till we drop our AI Performance results in our benchmark test 🥰 i can see the vision on this and will be curious to how Voxtral will compare to other loads Also can't wait to try them out

Profilbild von James

Jamesvor 6 Monaten

@MistralAI is this multithreaded? what kind of cpu/gpu usage does it have?

Profilbild von Alexandre Mendes

Alexandre Mendesvor 6 Monaten

@MistralAI can i use it on a second window in youtube?

Profilbild von Jaga behera - NISM Certified

Jaga behera - NISM Certifiedvor 6 Monaten

🚨 AI Tech Update Real-time speech transcription is now possible directly in your browser with Voxtral WebGPU. • Runs Voxtral‑Mini‑4B locally using WebGPU • Developed by Mistral AI • Supports 13 languages • <500 ms latency for near real-time transcription • Fully private processing happens on your device • Zero cost, no cloud required A glimpse into the future of on-device AI and private speech recognition. #AI #SpeechRecognition #WebGPU #MistralAI

Profilbild von LightShift Studio

LightShift Studiovor 6 Monaten

@MistralAI 🎙️ Hey Insta fam!

Profilbild von richardanaya2_2048b.Q6_K.gguf 🇺🇸🤖

richardanaya2_2048b.Q6_K.gguf 🇺🇸🤖vor 6 Monaten

@MistralAI Does this run on Oculus Quest chrome browser?

Profilbild von 0xShugo

0xShugovor 2 Monaten

@MistralAI C++/GGML based Voxtral Mini 4B Realtime released! 16.39x (0.0610 RTF) realtime offline, 170ms TTFT streaming on RTX 5090.

Profilbild von Ariel Jankelowitz

Ariel Jankelowitzvor 6 Monaten

@MistralAI Amazing, can’t wait to integrate this.

Profilbild von Melvin Vivas

Melvin Vivasvor 6 Monaten

@MistralAI wow, must try this

Profilbild von Koshur AI

Koshur AIvor 6 Monaten

@MistralAI

Profilbild von kaiyes

kaiyesvor 6 Monaten

@MistralAI this should be able to transcribe youtube videos right ?

Profilbild von Kim Hjortholm

Kim Hjortholmvor 6 Monaten

@MistralAI Argh, no support for Danish - my test got transmogrified to Dutch 😂 Which actually makes sense as the best guess in the lack of Danish support

Profilbild von kfant

kfantvor 6 Monaten

@MistralAI yea but new granite by ibm ...

Profilbild von Faust

Faustvor 6 Monaten

@MistralAI Been waiting for something like this. Running a 4B model locally with sub-500ms latency is wild—WebGPU keeps unlocking new possibilities.

Profilbild von Victor

Victorvor 6 Monaten

@Scobleizer @MistralAI lol the fact that this runs entirely in browser with zero backend is kind of insane, been waiting for local speech-to-text that actually works 😭

Ähnliche Videos

Introducing Voxtral WebGPU: State-of-the-art audio transcription directly in your browser! 🤯 🗣️ Transcribe videos, meeting notes, songs and more 🔐 Runs on-device, meaning no data is sent to a server 🌎 Multilingual (8 languages) 🤗 Completely free (forever) & open source

Introducing Voxtral WebGPU: State-of-the-art audio transcription directly in your browser! 🤯 🗣️ Transcribe videos, meeting notes, songs and more 🔐 Runs on-device, meaning no data is sent to a server 🌎 Multilingual (8 languages) 🤗 Completely free (forever) & open source

Xenova

20,060 Aufrufe • vor 1 Jahr

Introducing Phi-3 WebGPU, a private and powerful AI chatbot that runs locally in your browser, powered by 🤗 Transformers.js and onnxruntime-web! 🔒 On-device inference: no data sent to a server ⚡️ WebGPU-accelerated (> 20 t/s) 📥 Model downloaded once and cached Try it out! 👇

Introducing Phi-3 WebGPU, a private and powerful AI chatbot that runs locally in your browser, powered by 🤗 Transformers.js and onnxruntime-web! 🔒 On-device inference: no data sent to a server ⚡️ WebGPU-accelerated (> 20 t/s) 📥 Model downloaded once and cached Try it out! 👇

Xenova

117,724 Aufrufe • vor 2 Jahren

It's finally possible: real-time in-browser speech recognition with OpenAI Whisper! 🤯 The model runs fully on-device using Transformers.js and ONNX Runtime Web, and supports multilingual transcription across 100 different languages! 🔥 Check out the demo (+ source code)! 👇

It's finally possible: real-time in-browser speech recognition with OpenAI Whisper! 🤯 The model runs fully on-device using Transformers.js and ONNX Runtime Web, and supports multilingual transcription across 100 different languages! 🔥 Check out the demo (+ source code)! 👇

Xenova

262,819 Aufrufe • vor 2 Jahren

An open-weight alternative to ElevenLabs! Voxtral is a TTS model by Mistral with: - just 4B params - 70ms latency for voice agents - voice cloning from 3s of audio - 9 languages + cross-lingual transfer - 68.4% win rate over ElevenLabs Flash v2.5 Open weights on Hugging Face.

An open-weight alternative to ElevenLabs! Voxtral is a TTS model by Mistral with: - just 4B params - 70ms latency for voice agents - voice cloning from 3s of audio - 9 languages + cross-lingual transfer - 68.4% win rate over ElevenLabs Flash v2.5 Open weights on Hugging Face.

Avi Chawla

28,162 Aufrufe • vor 5 Monaten

Real-time video captioning in your browser with @LiquidAI's LFM2-VL model on WebGPU. Sending every frame to a server was never going to be the answer. Imagine the bandwidth, latency and cost. Local inference. No server costs. Infinitely scalable. This is the way.

Real-time video captioning in your browser with @LiquidAI's LFM2-VL model on WebGPU. Sending every frame to a server was never going to be the answer. Imagine the bandwidth, latency and cost. Local inference. No server costs. Infinitely scalable. This is the way.

Xenova

48,798 Aufrufe • vor 6 Monaten

This is what happens when you plug LLMs into voice assistants, instead of a decade of handwritten rules. This video dissects Voxtral (a family of OSS speech models) and the foundational work behind it (audio tokenization, semantic/acoustic disaggregation, etc). Thank you Mistral AI for your collaboration and for your detailed technical reports in an increasingly opaque industry! 00:00 Intro 01:03 Modular vs end-to-end speech models 03:30 Speech-to-Text 06:07 Delayed Streams Modeling (DSM) 09:41 Whisper Streaming 10:33 Voxtral Realtime 13:07 Voxtral Text-to-Speech 14:28 Throwback: WaveNet 15:24 Audio tokenization 20:39 The Voxtral Codec 21:49 Back to Voxtral TTS 25:30 Outro

This is what happens when you plug LLMs into voice assistants, instead of a decade of handwritten rules. This video dissects Voxtral (a family of OSS speech models) and the foundational work behind it (audio tokenization, semantic/acoustic disaggregation, etc). Thank you Mistral AI for your collaboration and for your detailed technical reports in an increasingly opaque industry! 00:00 Intro 01:03 Modular vs end-to-end speech models 03:30 Speech-to-Text 06:07 Delayed Streams Modeling (DSM) 09:41 Whisper Streaming 10:33 Voxtral Realtime 13:07 Voxtral Text-to-Speech 14:28 Throwback: WaveNet 15:24 Audio tokenization 20:39 The Voxtral Codec 21:49 Back to Voxtral TTS 25:30 Outro

Julia Turc

298,418 Aufrufe • vor 3 Monaten

NEW: LiquidAI just released LFM2.5-350M, a tiny model that brings agentic AI and tool-calling capabilities to resource-constrained environments. 🤯 It can even run locally in your browser via WebGPU, serving as a powerful companion while you browse the web. Try the demo! 👇

NEW: LiquidAI just released LFM2.5-350M, a tiny model that brings agentic AI and tool-calling capabilities to resource-constrained environments. 🤯 It can even run locally in your browser via WebGPU, serving as a powerful companion while you browse the web. Try the demo! 👇

Xenova

26,267 Aufrufe • vor 6 Monaten

NEW: Mistral AI releases Mistral 3, a family of multimodal models, including three start-of-the-art dense models (3B, 8B, and 14B) and Mistral Large 3 (675B, 41B active). All Apache 2.0! 🤗 Surprisingly, the 3B is small enough to run 100% locally in your browser on WebGPU! 🤯

NEW: Mistral AI releases Mistral 3, a family of multimodal models, including three start-of-the-art dense models (3B, 8B, and 14B) and Mistral Large 3 (675B, 41B active). All Apache 2.0! 🤗 Surprisingly, the 3B is small enough to run 100% locally in your browser on WebGPU! 🤯

Xenova

225,295 Aufrufe • vor 10 Monaten

RF-DETR, the state-of-the-art model series for real-time object detection, can now run 100% locally in your browser on WebGPU with 🤗 Transformers.js v4! The models are Apache-2.0 licensed, making them a perfect fit for both personal and commercial applications. Try the demo 👇

RF-DETR, the state-of-the-art model series for real-time object detection, can now run 100% locally in your browser on WebGPU with 🤗 Transformers.js v4! The models are Apache-2.0 licensed, making them a perfect fit for both personal and commercial applications. Try the demo 👇

Xenova

77,179 Aufrufe • vor 7 Monaten

Florence-2, the new vision foundation model by Microsoft, can now run 100% locally in your browser on WebGPU, thanks to Transformers.js! 🤗🤯 It supports tasks like image captioning, optical character recognition, object detection, and many more! 😍 WOW! Demo (+ source code) 👇

Florence-2, the new vision foundation model by Microsoft, can now run 100% locally in your browser on WebGPU, thanks to Transformers.js! 🤗🤯 It supports tasks like image captioning, optical character recognition, object detection, and many more! 😍 WOW! Demo (+ source code) 👇

Xenova

88,782 Aufrufe • vor 2 Jahren

I trained a small model to do syntax highlighting in the browser with GPU. Meet gpu-lexer from Vercel Labs: Small (27.5KB), fast (runs on WebGPU), and language-agnostic (model guesses the syntax). It is experimental and built for learning!

I trained a small model to do syntax highlighting in the browser with GPU. Meet gpu-lexer from Vercel Labs: Small (27.5KB), fast (runs on WebGPU), and language-agnostic (model guesses the syntax). It is experimental and built for learning!

Shu

794,606 Aufrufe • vor 22 Tagen

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.

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 7 Monaten

The era of 1-bit LLMs is here — now with WebGPU acceleration! 🤯 It's incredible to think that a quantized 1.7B model (just 290MB in size) can run at ~100 tokens per second entirely in your browser. Try the demo yourself 👇

The era of 1-bit LLMs is here — now with WebGPU acceleration! 🤯 It's incredible to think that a quantized 1.7B model (just 290MB in size) can run at ~100 tokens per second entirely in your browser. Try the demo yourself 👇

Xenova

105,543 Aufrufe • vor 5 Monaten

Introducing Granite Docling WebGPU 🐣 State-of-the-art document parsing 100% locally in your browser! 🤯 🔐 No data sent to a server (private & secure) 💰 Completely free... forever! 🔂 Docling ecosystem enables conversion to HTML, Markdown, JSON, and more! Try out the demo! 👇

Introducing Granite Docling WebGPU 🐣 State-of-the-art document parsing 100% locally in your browser! 🤯 🔐 No data sent to a server (private & secure) 💰 Completely free... forever! 🔂 Docling ecosystem enables conversion to HTML, Markdown, JSON, and more! Try out the demo! 👇

Xenova

55,978 Aufrufe • vor 11 Monaten

Mistral just released Voxtral TTS, an open-weight voice model that tries to match ElevenLabs while keeping it free. A 3-billionn param model that fits on a laptop and runs 6X faster than real-time speech. It is split into 3 parts that handle different jobs. - The 3.4B part is the main language brain that understands the text and plans what should be spoken. - The 390M part turns that plan into speech features like rhythm, pronunciation, and tone. - The 300M part converts those speech features into the final compressed audio signal you can play. That split helps because each part only does the job it is best at, which can make the whole system faster and lighter than one giant model doing everything alone. Mistral claims about 90ms to first audio, about 6x faster than real-time speech output, about 3GB RAM after quantization, 9 languages, and voice copying from 5s of audio, even across languages. Its internal tests report 62.8% preference over ElevenLabs Flash on default voices and 69.9% on custom voices, but the bigger point is that companies can keep speech data on their own machines. IMO, enterprise buyers usually care most about control, cost, and latency, So this model should give it great push for voice-based AI apps/products.

Mistral just released Voxtral TTS, an open-weight voice model that tries to match ElevenLabs while keeping it free. A 3-billionn param model that fits on a laptop and runs 6X faster than real-time speech. It is split into 3 parts that handle different jobs. - The 3.4B part is the main language brain that understands the text and plans what should be spoken. - The 390M part turns that plan into speech features like rhythm, pronunciation, and tone. - The 300M part converts those speech features into the final compressed audio signal you can play. That split helps because each part only does the job it is best at, which can make the whole system faster and lighter than one giant model doing everything alone. Mistral claims about 90ms to first audio, about 6x faster than real-time speech output, about 3GB RAM after quantization, 9 languages, and voice copying from 5s of audio, even across languages. Its internal tests report 62.8% preference over ElevenLabs Flash on default voices and 69.9% on custom voices, but the bigger point is that companies can keep speech data on their own machines. IMO, enterprise buyers usually care most about control, cost, and latency, So this model should give it great push for voice-based AI apps/products.

Rohan Paul

15,672 Aufrufe • vor 6 Monaten

Bonsai 27B just changed the local LLM game forever. 1-bit quantization shrinks it from 54GB to just 3.8GB (-93%), while retaining 90% of its intelligence. That's insane. With custom WebGPU kernels written by Fable 5 and GPT 5.6 Sol, the model now runs locally in your browser!

Bonsai 27B just changed the local LLM game forever. 1-bit quantization shrinks it from 54GB to just 3.8GB (-93%), while retaining 90% of its intelligence. That's insane. With custom WebGPU kernels written by Fable 5 and GPT 5.6 Sol, the model now runs locally in your browser!

Xenova

211,255 Aufrufe • vor 2 Monaten

Cyansdk is a free Blender AI motion capture plugin that runs locally on your computer. It requires 8GB of GPU memory for real-time processing and has a model size of 4.2GB. It supports real-time motion capture via webcam and video upload.

Cyansdk is a free Blender AI motion capture plugin that runs locally on your computer. It requires 8GB of GPU memory for real-time processing and has a model size of 4.2GB. It supports real-time motion capture via webcam and video upload.

CYANPUPPETS

16,350 Aufrufe • vor 1 Jahr

Okay, this is actually insane... You can now run LFM2.5-1.2B-Thinking (a 1.2B parameter LLM from @LiquidAI) at over 200 tokens per second directly in your browser on WebGPU! 🤯 Zero install. Fully private. Blazingly fast. Powered by Transformers.js and ONNX Runtime Web

Okay, this is actually insane... You can now run LFM2.5-1.2B-Thinking (a 1.2B parameter LLM from @LiquidAI) at over 200 tokens per second directly in your browser on WebGPU! 🤯 Zero install. Fully private. Blazingly fast. Powered by Transformers.js and ONNX Runtime Web

Xenova

104,476 Aufrufe • vor 7 Monaten

I seriously cannot believe this is a 0.6B LLM! 🤯 Qwen just released Qwen3, a series of hybrid reasoning models that allow you to control how much "thinking" the model does for a given task. They can even run locally in your browser on WebGPU with 🤗 Transformers.js!

I seriously cannot believe this is a 0.6B LLM! 🤯 Qwen just released Qwen3, a series of hybrid reasoning models that allow you to control how much "thinking" the model does for a given task. They can even run locally in your browser on WebGPU with 🤗 Transformers.js!

Xenova

74,954 Aufrufe • vor 1 Jahr

You don't need a GPU to run text-to-speech anymore. Kyutai released Pocket TTS, a 100 million parameter speech model that runs entirely on CPU. How it performs: > Nearly 6x faster than real time on a MacBook CPU > First audio chunk arrives in about 200 milliseconds > Runs on just 2 CPU cores > Supports voice cloning and 6 languages Setup takes one command: pip install pocket-tts Text-to-speech that used to need a GPU or a paid API now runs locally, on a laptop, in near real time.

You don't need a GPU to run text-to-speech anymore. Kyutai released Pocket TTS, a 100 million parameter speech model that runs entirely on CPU. How it performs: > Nearly 6x faster than real time on a MacBook CPU > First audio chunk arrives in about 200 milliseconds > Runs on just 2 CPU cores > Supports voice cloning and 6 languages Setup takes one command: pip install pocket-tts Text-to-speech that used to need a GPU or a paid API now runs locally, on a laptop, in near real time.

Simplifying AI

14,391 Aufrufe • vor 1 Monat