Scribe 2 Realtime is ElevenLabs's language model. A real-time speech-to-text model that streams transcription over WebSocket with voice-activity-based commits, word timestamps, and language detection.
Specifications
Canonical IDelevenlabs-scribe-2-realtime
TypeLanguage
StatusActive
CreatorElevenLabsElevenLabs
Input ModalitiesText
Output ModalitiesText
Release Date · 7 days ago

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Scribe 2 Realtime———Current
Scribe 2———Available
Scribe 1————Available
Scribe 1 Experimental————Available

Model IDs

elevenlabs-scribe-2-realtime
elevenlabs/scribe-v2-realtime