Fact · Languages and accents
When a request lists several languages, Google's service transcribes the audio using one best-fit language from that list.
Checked against its source on October 17, 2026
In the source's own words
“In a request with multiple languages, Cloud Speech-to-Text attempts to transcribe the audio using the best-fit language from the list of alternates you provided.”
Automatically detect language (Cloud Speech-to-Text documentation), Google, Google Cloud Documentation, 2026, Automatically detect language.
Open the original- What it measures
- The service then labels the result with the language code it chose.
- What it does not show
- This describes the request-level behavior in the documentation. It is not a claim about how the service handles a switch inside one sentence.