Google announces Gemini 3.5 Transcribe for AI-powered speech-to-text
The AI that powers Gboard's Rambler is coming to more Google products, including Chrome.
Google has unveiled Gemini 3.5 Transcribe, an AI-powered model aimed at simplifying voice input by eliminating filler words and corrections, ultimately producing refined AI-generated text. The model is already integrated into the Gboard Rambler feature on the Pixel 11, but it's set to expand across the Google ecosystem. According to Google, Gemini 3.5 Transcribe significantly outperforms its predecessor, Chirp 3, in terms of speed and accuracy.
The new model processes voice inputs about 70% faster than Chirp 3, transforming raw speech into finished transcribed text much more rapidly. Moreover, the live-speech error rate has been reduced to 5.5%, a slight improvement over Chirp 3's 7.32%. While the enhancement may seem minor, it significantly reduces the frustration of correcting typos when using voice input.
Written by urgent.news from Ars Technica's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
- Google brings Gemini Enterprise to lawyers with new AI tools, automation plug-ins indianexpress.com
- Google just fixed one of the most annoying things about talking to AI — Gemini Live can finally handle interruptions techradar.com
- Google’s Gemini has a branding problem, and so does the rest of AI techcrunch.com
- Google rolls out Gemini Audio to improve real-time dialogue and speech recognition androidauthority.com
- Google debuts Gemini 3.5 Transcribe, a speech-to-text model that powers Gboard Rambler and is coming to Chrome, in public preview for developers and enterprises (Abner Li/9to5Google) 9to5google.com
- Gemini's one billion users can't hide Google's cash flow crisis androidpolice.com
- Google's Gemini 3.5 Transcribe converts raw audio into formatted text seekingalpha.com
