ElevenLabs released Scribe v3 and Scribe v3 Live speech recognition models
The story so far
ElevenLabs has released Scribe v3 and Scribe v3 Live speech recognition models, aimed at improving the recognition performance of voice agents during calls. Scribe v3 is suitable for pre-recorded audio, while Scribe v3 Live is designed for low-latency real-time applications, especially to prevent voice agents from cutting off users during calls by leveraging conversational context.
AI-written from the reports · Updated 2 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- The DecoderElevenLabs Scribe v3 Live released, prevents voice AI agents from cutting off users during calls through conversation context.
ElevenLabs releases Scribe v3 and Scribe v3 Live speech-to-text models, Scribe v3 is suitable for pre-recorded audio in noisy environments, Scribe v3 Live is suitable for low-latency real-time applications.
Heat over time
- Now
- 3
- Peak
- 1012 Nov, 23:00
- 24h change
- -49%
Hover or tap the chart to see each hour; use the arrow keys on a keyboard.