--- format: "aidr-story-markdown/v1" id: "64fc2a8f84c91b7ab28f97ed627bb801987f761235eb0d27f501b4d90f9f834b" canonical_url: "https://aidr.today/64fc2a8f?lang=en" title: "Dev's Google AI Hack Transcribes 1 Hour of Audio in 13 Seconds" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-10-12T18:38:24.000Z" category: "Models" topics: ["google","inference"] source_urls: ["https://marketbrief.now/ai/update-devs-google-ai-hack-transcribes-1-hour-of-audio-in-13-seconds-7e92e69f","https://x.com/TslShahir/status/2109660368381395414","https://x.com/GoogleDeepMind/status/2107502289652982118","https://x.com/ivanfioravanti/status/2109277085068148746","https://x.com/Alex_tra_memory/status/2108391275560931355","https://x.com/SeraAndroid/status/2108629662238961694","https://x.com/fdaudens/status/2109305611674333207","https://x.com/ClementDelangue/status/2107550827527463068"] summary: "A developer repurposed the EmbeddingGemma 2 multimodal model into a speech-to-text tool that can transcribe one hour of audio in approximately 13 seconds on a base M3 MacBook Air. The 740M parameter model was released by Google under an Apache 2.0 license and supports local Mac applications like DigUp and Foresight." --- # Dev's Google AI Hack Transcribes 1 Hour of Audio in 13 Seconds > [Open the canonical story]() **Published:** 2026-10-12T18:38:24.000Z **Category:** Models **Topics:** google, inference ## Summary A developer repurposed the EmbeddingGemma 2 multimodal model into a speech\-to\-text tool that can transcribe one hour of audio in approximately 13 seconds on a base M3 MacBook Air\. The 740M parameter model was released by Google under an Apache 2\.0 license and supports local Mac applications like DigUp and Foresight\. ## Sources - [Story source]() - [Story source]() - [Story source]() - [Supporting source]() - [Story source]() - [Supporting source]() - [Supporting source]() - [Supporting source]()