ElevenLabsAudio modelActive

Scribe v3 Live

Summary

Scribe v3 Live is ElevenLabs' real-time model for streaming speech. The provider released it on November 10, 2026. API model ID `scribe_v3_live` uses the Speech to Text WebSocket. Documented capabilities include 90+ languages, turn prediction from conversation context, mid-sentence language switching, and diarization during streaming.

The model is available through ElevenAPI and ElevenAgents. The documentation also provides a web demo for Speech to Text. The API rate is USD 0.22 per hour of processed audio. Public weights are not documented.

Similar models

More models of the same kind as Scribe v3 Live, chosen by model line, developer, size, price and release date.

More about Scribe v3 Live

All specifications

Architecture

Model class: Real-time model for streaming speech transcription; Source: Model class

Input and output

Input: Audio stream; Source: Input
Output: Text; Source: Output
Capabilities: Supports 90+ languages, streaming, word-level timestamps, real-time diarization, language switches within a sentence, and context-based turn prediction. The keyterm library holds up to 10,000 terms, in addition to up to 50 standard keyterms.; Source: Capabilities

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking: Unknown; no source
Watermarking technique: Not known; no source

Licence and access

Access: Available through ElevenAPI and ElevenAgents. The documentation also provides a web demo for Speech to Text.; Source: Access
Shutdown: None announced; no source

API

API model ID: scribe_v3_live; Source: API model ID

Further details

Predecessor: Successor to Scribe v2 Realtime; Source: Predecessor
Weights and license: Hosted proprietary service; public downloadable weights are not documented.; Source: Weights and license

Prices

API price: USD 0.22 per hour of processed audio.Source

Sources and data date

Type	Evidence and data date
Additional source	ElevenLabs Scribe v3 announcement (retrieved November 11, 2026) · ElevenLabs Scribe v3 announcement · Editorial description reviewed November 11, 2026
Additional source	ElevenLabs model documentation (retrieved November 11, 2026) · ElevenLabs model documentation · Editorial description reviewed November 11, 2026
Additional source	ElevenLabs speech-to-text documentation (retrieved November 11, 2026)
Additional source	ElevenLabs API pricing (retrieved November 11, 2026) · ElevenLabs API pricing · Editorial description reviewed November 11, 2026