Fact · Speech recognition
Google's general Gemini audio guide says that for dedicated speech-to-text models with real-time transcription, you should use the Google Cloud Speech-to-Text API.
Checked against its source on October 17, 2026
In the source's own words
“For dedicated speech to text models with support for real-time transcription, use the Google Cloud Speech-to-Text API”
Audio understanding (Gemini API), Google, Google AI for Developers, 2026, Overview.
Open the original- What it measures
- This sentence appears in the overview of Google's audio guide, read on 2026-10-17. The live transcription guide, read the same day, describes a real-time transcription model inside the Gemini API.
- What it does not show
- The two Google pages disagree. The sentence may describe older guidance, and the live transcription guide is the more specific of the two for the Gemini model. Check both before you choose a product.