Developer Turns EmbeddingGemma 2 into Fast On-Device Speech-to-Text

Developer @TslShahir repurposed Google's open-source EmbeddingGemma 2 into a speech-to-text model that transcribes an hour of audio in about 13 seconds on a base M3 MacBook Air, making it one of the fastest on-device STT solutions.

2026-10-13 ~ 2026-10-13 · 2 related posts

• Dev turns EmbeddingGemma 2 into an on-device STT model, transcribing 1 hour of audio in 13 seconds — solyarisoftware · 2026-10-13
• Embedding model turned into STT: M3 MacBook Air transcribes 1hr audio in 13s — TheMoonMidas · 2026-10-13