SPEECH TO TEXT

ElevenLabs launches Scribe v3 and v3 Live for recorded and streaming audio

By IDAKIM Digital · Published November 11, 2026

The paired transcription models add speaker-labeling improvements, terminology controls and conversational turn prediction.

ElevenLabs released Scribe v3 for recordings and Scribe v3 Live for realtime audio on November 10. Both are available through ElevenAPI, and the live model is also offered in ElevenAgents. The provider reports lower error rates than the preceding models across its evaluations; recorded word error and live semantic word error use different measures and should not be compared as one accuracy score. Live transcription gains diarization and turn detection that considers conversational context alongside audio, aiming to reduce interruptions during pauses. The recorded model supports keyterm prompting and output-format controls, while the live model adds multilingual switching and a larger keyterm-library option. US processing is the default. Isolated regional environments and Zero Retention Mode are described as deployment options, not a blanket assurance that every request uses those settings. Changing the model ID may be straightforward, but downstream summaries and voice-agent actions still need evaluation on real accents, numbers and product vocabulary.

Why it matters

Use consented recordings to compare word accuracy, speaker assignment and turn timing separately. Confirm retention and regional settings before sending sensitive audio, and verify critical names or numbers.

Source: ElevenLabs · November 10, 2026

Product claims are attributed to the linked publisher. IDAKIM Digital has not independently tested these claims.