AIThe Decoderabout 2 hours ago
Google launches Gemini 3.5 Transcribe speech-to-text model
1 min read
Google announced Gemini 3.5 Transcribe, an AI speech-to-text model supporting 85 languages with filler-word removal and on-the-fly corrections. It is 70 percent faster than Chirp 3, with a 5.5 percent live-speech error rate. The model powers Gboard's Rambler on Pixel 11 and expands to more Google products.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyGoogle
Summary by ByteBrief
