According to Google, Gemini 3.5 Transcribe is a speech-to-text model designed for intelligent real-time transcription across 85+ languages with custom vocabulary recognition, handling live language switches and background noise. Google also released Gemini Omni 1.1 Flash with video production controls including scene extension, first and last frame interpolation, and 4K upscaling. Both models are available through Google AI Studio and the Gemini Enterprise Agent Platform.
Topics #
Sources #
- Official
[Read article](https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-5-transcribe/) - Official
[Read article](https://blog.google/innovation-and-ai/technology/developers-tools/build-with-gemini-omni-1-1-flash/)
Go deeper #
This intelligence is sourced automatically from public sources across the web and synthesised by the Prefactor AI pipeline. Stories are reviewed before publication.
source & further reading
getreadyforagents.com — original article
Model Context Protocol registry reaches 72 servers with integration support for multiple AI models
OpenAI experiences high-profile executive departures including infrastructure leadership
Anthropic merges Claude Chat and Cowork memory systems with opt-out privacy model