Google DeepMind released Gemini 3.5 Transcribe, an intelligent speech-to-text model designed for clean and structured audio transcription across 85+ languages, now live in Antigravity and AI Studio.
Key Takeaways
- ✓Significantly improved entity recovery for phone numbers, postal codes, and code snippets in noisy audio;
- ✓Intelligent filler word removal, automated formatting, and custom dictionary support across 85+ languages;
- ✓Day-0 availability in macOS Gemini app, Android Gboard, and developer platforms including Antigravity.