Fact · Transcription
Google's Gemini audio documentation lists transcription and translation of speech among the things a Gemini model can do with audio input, alongside describing, summarizing and answering questions about the audio.
Checked against its source on October 17, 2026
In the source's own words
“Transcription and translation (speech to text) Speaker diarization (identifying different speakers)”
Audio understanding (Gemini API), Google, Google AI for Developers, 2026, Audio understanding overview, use cases.
Open the original- What it measures
- The page is the developer guide for the Gemini API. Its example asks a Gemini model to transcribe a recording, give the English translation of each segment that is not in English, and return the result as structured output.