Export
The link always opens the latest version of this page.
Ask an AI about it
Open in ChatGPTA new chat that reads this entry from the site Open in ClaudeThe same, in ClaudeShare the link instead of a file, and they will always see the latest version.
Files are a snapshot of today. The live page has anything newer.
Gemini 3.5 Transcribe
Speech-to-text model for real-time and pre-recorded audio transcription with intelligent formatting, custom vocabulary, and multilingual support.
- Category
- speech-to-text model 1 source
Gemini 3.5 Transcribe is a speech-to-text model developed by Google 1 for transcribing real-time and pre-recorded audio with intelligent formatting, custom vocabulary, and multilingual support 1.
The model is available across multiple platforms, including Android and macOS 1, as well as through the Gemini API, Live API, and Interactions API 2.
Facts 2
| Attribute | Value | Confidence | Sources | Cited |
|---|---|---|---|---|
| Vendor | low | 1 | 1 | |
| Category | speech-to-text model | low | 1 | 1 |
Platform 2
- Android, →macOS, →Gemini API, →Live API, →Interactions API
- Gemini API, Live API, Interactions API
Neighbourhood
Developed by 1
Supersedes 1
Official links
Frequently mentioned together 12
Sources 7
- Intelligent transcription with Gemini 3.5 Transcribe · Google Security Blog
- Intelligent transcription with Gemini 3.5 Transcribe · Google DeepMind
- Gemini 3.8 text-to-speech says hello · Google DeepMind
- Build real-time voice applications with Gemini 3.8 Live and 3.5 Transcribe · Google Security Blog
- AI for everyone in every language · Google Security Blog
5 of 7 sources shown · Pro unlocks the full list