Skip navigation
Introducing Voxtral WebGPU: Real-time speech transcription entirely in your browser.
0:00 / 0:39

Introducing Voxtral WebGPU: Real-time speech transcription entirely in your browser.

Xenova

@xenovacom21K followers

Visit on X
552 likesDownloadOriginal post

94,711 views

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.

28 Comments

Comments from the original post on X (Twitter)

  • Xenova's profile picture

    @xenovacom

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

    43 likes

  • Vlad's profile picture

    @deifosv

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

    3 likes

  • Xenova's profile picture

    @xenovacom

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

    1 like

  • Vlad's profile picture

    @deifosv

    @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.

    1 like

  • DrFlask's profile picture

    @rje4242

    @MistralAI

    3 likes

  • Xenova's profile picture

    @xenovacom

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

    4 likes

  • DrFlask's profile picture

    @rje4242

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

  • matt palmer's profile picture

    @mattyp

    @MistralAI lets goooo!

    2 likes

  • Xenova's profile picture

    @xenovacom

    @MistralAI You called it 😂

    3 likes

  • matt palmer's profile picture

    @mattyp

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

    1 like

  • Haydon Ryan 🇦🇺🇺🇸's profile picture

    @haydonryan

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

    1 like

  • Cesar Bonadio's profile picture

    @C_Bonadio

    @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!

    1 like

  • 岡田泰彦|光邦|AI×印刷エヴァンジェリスト's profile picture

    @KohoOkada

    @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。

    1 like

  • GPUBenchTest.com's profile picture

    @GPUBenchTest_

    @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

  • James's profile picture

    @AwokeKnowing

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

  • Alexandre Mendes's profile picture

    @alexandre_rme1

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

  • Jaga behera - NISM Certified's profile picture

    @jagaa_official

    🚨 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

  • LightShift Studio's profile picture

    @LightShiftHQ

    @MistralAI 🎙️ Hey Insta fam!

  • richardanaya2_2048b.Q6_K.gguf 🇺🇸🤖's profile picture

    @richardanaya

    @MistralAI Does this run on Oculus Quest chrome browser?

  • 0xShugo's profile picture

    @0xShug0

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