Google unveils Gemini 3.5 Transcribe, an AI model that cleans up voice input

Google has announced Gemini 3.5 Transcribe, an AI model designed to improve speech-to-text by removing verbal stumbles like "ums" and producing polished text. The model already powers the Rambler feature in Gboard on the Pixel 11 and will soon expand across Google's ecosystem.

According to Google, it is about 70 percent faster than its predecessor, Chirp 3, and has a lower live-speech error rate of 5.5 percent compared to 7.32 percent. While the accuracy gain is modest, the speed and convenience improvements make it a useful upgrade for voice input.

vidgetc Tech, gaming & AI news — always at hand Google Play · Soon App Store · Soon
💬 Discuss

Comments

Next articleStanford Study: AI Impact Falls Heaviest on Entry-Level Workers
Start typing to search