Product

Scribe (Speech to Text)

by ElevenLabs · Speech-to-Text

What it does

Transcribes audio into text across 90+ languages with speaker diarization, word-level timestamps, and non-speech event tagging.

Key features

  • Sub-150ms realtime latency (v2 Realtime)
  • Speaker diarization
  • Word-level timestamps
  • Automatic language detection
  • EU/India data residency

Integrations

REST APIWebSocket streamingElevenAgents