Skip to content

AI · AI today, November 11, 2026

Tools

ElevenLabs launches Scribe v3 and a real-time model for speech transcription

· Aster editorial team

Blue and cream acoustic waves pass through a brass listening instrument.AI-generated image

ElevenLabs launched Scribe v3 for recorded audio and Scribe v3 Live for low-latency transcription. The real-time version adds speaker diarization and conversation-aware turn detection, while both models support specialized vocabularies. In company tests, Scribe v3 produced 27 % fewer word errors than Scribe v2 across 102 languages, and Live produced 43 % fewer errors than its predecessor.

Why it matters

Better speaker and turn separation could reduce interruptions and corrections in voice agents, captions, and documentation, although the figures come from ElevenLabs' own evaluations.

For the technical crowd

Scribe v3 Live is available in ElevenAgents, and both models can be used through ElevenAPI. Multilingual mode supports language switching within a sentence.

· Source: ElevenLabs

More from AI today

See all of the day’s stories · Whole section