ElevenLabs' most accurate realtime speech-to-text model, with turn prediction and live diarization across 90+ languages. Served through the gateway's /v1/realtime WebSocket endpoint in ElevenLabs' native realtime protocol, billed per hour of audio sent.
LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.
ElevenLabs' most accurate realtime speech-to-text model, with turn prediction and live diarization across 90+ languages. Served through the gateway's /v1/realtime WebSocket endpoint in ElevenLabs' native realtime protocol, billed per hour of audio sent. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for Scribe v3 Live on LLM Gateway starts at $0.00 per million input tokens and $0.00 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
Scribe v3 Live is served by ElevenLabs through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
No. Scribe v3 Live does not currently support tool calling or structured JSON outputs through LLM Gateway.
Scribe v3 Live was released on November 10, 2026.