ElevenLabs launches Scribe v3 and Scribe v3 Live speech-to-text models
Article timeline
The articles in this story. Times are ET.
ElevenLabsOfficialElevenLabs makes Scribe v3 Live available in ElevenAgents and ElevenAPIAIElevenLabs says Scribe v3 Live is now available in ElevenAgents, and both Scribe v3 models are available in ElevenAPI. Scribe v3 is also the default model in the ElevenLabs app.
- ElevenLabsOfficialElevenLabs releases Scribe v3 and Scribe v3 Live transcription models
AIElevenLabs says Scribe v3 has the best transcription and diarization accuracy of any model it tested. Scribe v3 Live adds diarization for the first time and makes 43% fewer errors than its predecessor. The company also says it added a key term library holding up to 10,000 terms and plain-English transcript editing.
- ElevenLabsOfficialElevenLabs introduces Scribe v3 and Scribe v3 Live speech-to-text models
AIElevenLabs says Scribe v3 and Scribe v3 Live are its most accurate speech-to-text models yet. The company says they handle extreme background noise, detect pauses at sentence ends, and track who said what in busy meetings.
- ElevenLabs BlogOfficialPickElevenLabs launches Scribe v3 and Scribe v3 Live speech-to-text models
AIElevenLabs launches Scribe v3 for recorded audio, which makes 27% fewer word errors than Scribe v2 across 102 languages. Scribe v3 Live, its realtime variant, makes 43% fewer errors than Scribe v2 Realtime and adds speaker diarization. Both models are available in ElevenAPI, and switching from Scribe v2 requires changing only the model ID.