Skip navigation
Introducing Moonshine Web: real-time speech recognition running 100% locally in your browser!
0:00 / 0:40

Introducing Moonshine Web: real-time speech recognition running 100% locally in your browser!

Xenova

@xenovacom20K followers

Visit on X
466 likesDownloadOriginal post

27,940 views

Introducing Moonshine Web: real-time speech recognition running 100% locally in your browser! 🚀 Faster and more accurate than Whisper 🔒 Privacy-focused (no data leaves your device) ⚡️ WebGPU accelerated (w/ WASM fallback) 🔥 Powered by ONNX Runtime Web and Transformers.js

11 Comments

Comments from the original post on X (Twitter)

  • Xenova's profile picture

    @xenovacom

    Huge shout-out to the Useful Sensors team for such an amazing model and to @waelyasmina for his 3D audio visualizer tutorial! 🤗 🧑‍💻 Source code: 🔗 Online demo:

    41 likes

  • AssemblyAI's profile picture

    @AssemblyAI

    Announcing: Our most advanced speech-to-text model goes beyond accuracy to capture the real-world complexity of human conversation and deliver reliable, source-of-truth audio data. Explore Universal-2 updates 👇

    3,452 likes

  • mr.niko.la's profile picture

    @diynikola

    How does it compare to whisper v3 L wrt speed ?

    3 likes

  • Eyal 🏐's profile picture

    @_Shaamallow

    The one man army strikes again!

    2 likes

  • Sean Aguinaga's profile picture

    @seanaguinaga

    ❤️

    1 like

  • Alex Volkov (Thursd/AI)'s profile picture

    @altryne

    well damn

    1 like

  • Vlad's profile picture

    @deifosv

    say what??? I will be testing this to see if i can add it to voice notes for what I'm building right now. Great work!

    1 like

  • omid's profile picture

    @omidaziz

    This is cool

    1 like

  • Addy Osmani's profile picture

    @addyosmani

    This looks so good. Is Moonshine Base multilingual or English? Using Whisper w/TF and will have to play with this.

    1 like

  • Xenova's profile picture

    @xenovacom

    The current generation of Moonshine models are English-only, but maybe the Useful Sensors team is planning on a multilingual model in future? 😁 @keveman

    2 likes

  • Ivan Fioravanti ᯅ's profile picture

    @ivanfioravanti

    WOW! Really cool!

    1 like