Google has announced Gemini 3.5 Transcribe, a new AI model designed to improve voice input by cleaning up hesitations and corrections in speech. The model already powers the Gboard Rambler feature on the Pixel 11 and will soon roll out across other Google products.
According to Google, it is roughly 70 percent faster than the previous Chirp 3 engine, with a live-speech error rate of 5.5 percent compared to Chirp 3's 7.32 percent. The release comes as users continue to wait for the larger Gemini 3.5 Pro model.
Comments