Embedding model turned into STT: M3 MacBook Air transcribes 1hr audio in 13s
TheMoonMidas · x · 2026-10-13
Developer @TslShahir repurposed Google's open-source EmbeddingGemma 2 embedding model into an on-device speech-to-text model, transcribing an hour of audio in 13 seconds on a base M3 MacBook Air — 288× real time, among the fastest on-device STT setups.
The idea came from Gemini Embedding 2 in March: it places text, images, audio and video in one shared embedding space, so a spoken word lands next to its written form, letting transcripts be read straight out of the embedding. The claim was only testable once EmbeddingGemma 2 shipped as an open model last week.
Related event: Developer Turns EmbeddingGemma 2 into Fast On-Device Speech-to-Text(2 posts)→
More from coding & agent
- Indie dev ships hosted scraping MCP: pay nothing when sites block you, 1000 free credits — SidMishraDev · 2026-10-13
- Cursor's new pricing: Claude and other third-party models billed at API rates, plans include only Grok — iannuttall · 2026-10-13
- Dev: vibe coders with Claude can't yet beat 15-year principal engineers — but he expects yes within a year — facontidavide · 2026-10-13
- Open-Source MCP Security Gate Blocks Prompt Injections in Under 5ms — EstablishmentTough18 · 2026-10-13
- Open-source Claude skill writes working prompts on first try for 18+ AI tools — nikola_mr64990 · 2026-10-13
- When does an internal AI agent tool deserve to become a standalone app? — Moist_Deal_9995 · 2026-10-13