AINewsnow

Running ffmpeg, Whisper and background removal in the browser: lessons learned

I ship a few "server-class" engines in plain static web pages: ffmpeg.wasm for video, Whisper for transcription, an ONNX segmentation model for background removal, and Tesseract for OCR. No backend at all. They all work, but each one taught me something. Here are the practical lessons. 1. Never loa…

Read the full story at DEV Community — Machine Learning ↗

Timeline · 1 report

  1. 2026-11-02 08:25 · DEV Community — Machine Learning
    Running ffmpeg, Whisper and background removal in the browser: lessons learned

More stories

  1. DeepL and Whisper Quietly Save Time — DEV Community — AI
  2. I built a free Whisper transcription site that runs in the browser: 5 things that broke — DEV Community — AI
  3. Echoes: a ghost in the machine that keeps your words and hands them back — DEV Community — AI
  4. How to transcribe a podcast by name, without an API key (2026) — DEV Community — AI
  5. OpenAI is making ChatGPT and Whisper available to third-parties — Mashable AI
  6. DeepSeek open-sources dsh-superagent, a proactive autonomous coding agent — Bloomberg AI
  7. Altman visits Samsung and SK as OpenAI rebrands data centres amid backlash — Tom's Guide AI
  8. Argentina's Milei pitches regulation-free AI haven at the end of the world — AP News

Get the daily brief of stories like this at 6:30 every morning →