Fact · Speech recognition
Google Cloud Speech-to-Text's speaker diarization detects when speakers change and labels each voice with a number, and it tags each word with the speaker number.
Checked against its source on October 17, 2026
In the source's own words
“detects when speakers change and labels by number the individual voices detected in the audio”
Detect different speakers in an audio recording (Cloud Speech-to-Text), Google Cloud, 2026, Speaker diarization section.
Open the original- What it measures
- Google's labels are numbers such as speaker 1 and speaker 2, not names. Matching numbers to people is a separate step.
- What it does not show
- Google's documentation describes the labels, not an accuracy figure for diarization.