Free Browser-Based Speech Recognition Tool Uses 3 Transformer Models for Diarization
doodlestein · x · 2026-08-13
A world-class multi-speaker speech recognition tool is gaining attention. It integrates three different Transformer models to provide not only high-quality ASR but also robust denoising and speaker diarization.
The tool is completely free, open-source, and runs entirely locally in the browser—meaning no audio data is uploaded, ensuring privacy. Tests show that while it may be slightly slower than the CLI version, the recognition quality is impeccable. It also supports exporting results as Markdown or self-contained HTML files for easy sharing.
Related event: Franken Whisper: Open-Source Browser-Based ASR Tool(3 posts)→
More from Apps
- A gallery of 214 projects built on one model shows the 'post your build' ad flywheel — gaganghotra_ · 2026-10-16
- Sill: free open-source tool streams any Mac window to iPhone/iPad with touch and Apple Pencil — jedisct1 · 2026-10-16
- Tesla's new Roadster UI revealed with retro-futuristic design aesthetic — tawnniee · 2026-10-16
- Excaliflow goes fully open-source: hand-drawn diagrams with live animated data flows in a single HTML file — Saboo_Shubham_ · 2026-10-16
- SEO consultant: Google could add utm_source tags to AI search citations to reveal real traffic — gaganghotra_ · 2026-10-16
- Google Dataset Search returns zero results for 24 hours, users blame AI scrapers — gaganghotra_ · 2026-10-16