Fact · Speech recognition
ElevenLabs says its Scribe speech-to-text API returns structured JSON transcripts with speaker diarization and word-level timestamps.
Checked against its source on October 17, 2026
In the source's own words
“to get structured JSON transcripts with speaker diarization and word-level timestamps”
Meet Scribe, ElevenLabs, 2025, Developer paragraph.
Open the original- What it measures
- This shows a hosted API that bundles diarization with transcription, which is one way to avoid a separate diarization step.
- What it does not show
- This describes the feature, not how accurate its speaker labels are. Test on your own recordings with several speakers.