Modelelevenlabs/scribe-v2-realtime
Scribe v2 Realtime
A real-time speech-to-text model from ElevenLabs that supports transcribing text while the user is speaking.
Timeline (last 90 days)
Oct 27
In a pipeline-style real-time voice setup, the official example uses Scribe v2 Realtime to transcribe a 16kHz microphone stream, sends the transcribed text to a language model (the example uses anthropic/claude-haiku-5.5), and then feeds the output into speech synthesis.
Unverified50%