Google releases Gemini 3.5 Transcribe with smart post-processing
GoogleDeepMind · x · 2026-08-27
Google DeepMind launched Gemini 3.5 Transcribe, a new speech-to-text model. Key features include:
- Enhanced Understanding: Better at complex phone numbers, postal codes, and order IDs in noisy environments.
- Smart Post-processing: Removes filler words and auto-formats text.
- Custom Vocab: Recognizes unique names and product titles.
- Multilingual: Detects and transcribes speech in 85+ languages.
Available now in Gemini app on macOS and Gboard on Android.
Related event: Google Launches Gemini 3.5 Transcribe Speech-to-Text Model(17 posts)→
More from Models
- From Torrent Links to API Gates: The Evolution of Open Weights Distribution — thursdai_pod · 2026-08-27
- Test: Codex Usage Seems Almost Unlimited Compared to Fable — panickssery · 2026-08-27
- Qwen and GLM push forward with low-cost, high-speed models — brandon_galang · 2026-08-27
- User Corrects Misinformation Regarding Qwen3.8-27B Model Rankings — Real-C- · 2026-08-27
- Rumor Suggests Imminent Release of Anthropic's Sonnet and Opus — ChrisGPT · 2026-08-27
- Qwen3.8-27B on AMD R9700 hits 227 tok/s with lossless block-diffusion drafter — samsja19 · 2026-08-27