What happened
Google has launched Gemini 3.5 Transcribe, a speech-to-text model for real-time transcription that auto-corrects slips of the tongue and strips filler words like "um."
Why it matters
Google reports a word error rate of 4.0 percent for streaming and 2.6 percent for recorded audio, with 70 percent lower latency than its predecessor, Chirp 3. The model can also hand off tasks like image generation or web searches to other Gemini models through "function calling."
What to watch
The model is available in Google AI Studio and on the Gemini Enterprise Agent Platform, and is already built into Gboard for Android and the Gemini app on macOS, with Chrome support coming soon.
Summaries like this, in your inbox every morning.
This launch follows Google's previous speech-to-text work with Chirp 3, and Gemini 3.5 Transcribe directly improves upon it by delivering 70 percent lower latency. The model is positioned for broad integration, already appearing in Gboard for Android and the Gemini app on macOS. Its ability to recognize over 85 languages automatically and format text by itself aims to make transcription more seamless.
The inclusion of "function calling" allows Gemini 3.5 Transcribe to pass tasks like image generation or web searches to other Gemini models. This suggests the transcription tool is designed not just to convert speech to text, but to act as a starting point in a chain of AI-driven actions. With Chrome support coming soon, its availability is set to expand beyond current platforms.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
Circlia started a proof-of-concept for TASTE SIGNAL: visitors to Holland Village Cafe FUKUOKA taste cookies an…
In a webinar hosted by French Mathematical Society president Isabelle Gallagher, Fields Medal winner Hugo Dumi…
NVIDIA released Nemotron 3.5 Super VL, an open-weight model with 120 billion parameters that handles text, ima…
NVIDIA released Nemotron 3.5 Bolt 74B-A9B 24GB, an AI model for local agents that hits over 80 tokens per seco…
NVIDIA published a blog post titled "AI Security Is an Engineering Problem - How to Solve It at Every Layer of…
In the test, Haiku 5.5 on medium setting averaged scores close to Sonnet 5.5 on routine documents at about 1/1…
