Did someone say Whisper + WebGPU in the browser? 👀
Super happy to see Transformers.js powering on-device transcription in @Remotion ❤️ timestamped words straight to captions, no server involved🚀
Nice work @JNYBGR & team 🙌
Some cool new packages we've made!
@remotion/whisper-webgpu: Transcribe audio in the browser
@remotion/gsap: Use GSAP to animate in Remotion
@remotion/mac-cursors: Every Mac cursor as vector graphic
Happy hacking 🥳 remotion.dev/api
Had a great time talking browser AI with @grabbou on React Universe On Air.
We went pretty deep: why Transformers.js sits on ONNX Runtime, what WebGPU changes, caching and download UX, agents in the browser, and a first look at the WebGPU inference engine we are building at
How much AI can you run in the browser today? @nicodotdev from @huggingface joins @grabbou to explain how Transformers.js brings pretrained models into JavaScript for text, audio, image, and agent workflows.
The conversation covers ONNX Runtime, WebGPU, model downloads and
Two days ago we shipped @huggingface/kernels. Now here's the deep dive.
Why we publish Jinja templates instead of WGSL files, how the browser compiles the fastest kernel for your GPU, and what that unlocks:
→ attention in 20 lines of JS, running on the GPU
→ 1M+ pixels
Background removal and transcription run in the browser. @nicodotdev joins @grabbou to cover Transformers.js today, device limits, offline use, and which parts of an agent workflow can already run locally.
📺 YouTube premiere: youtu.be/elAVSra9KCY
📆 Sept 7 at 2PM CEST
