ElevenLabs releases Scribe v2 Realtime speech-to-text model
Original title:Introducing Scribe v2 Realtime
AI summary
ElevenLabs released the real-time speech-to-text model Scribe v2 Realtime, with latency below 150 ms, 93.5% accuracy across 30 common European and Asian languages, and support for about 90 languages.
Key Takeaways
- ElevenLabs released the real-time speech-to-text model Scribe v2 Realtime
- with latency below 150 ms
- 5% accuracy across 30 common European and Asian languages,and support for about 90 languages.
Quick Facts
- Published
- Updated
- Source
- ElevenLabs:Blog(网页)
- Category
- Model Releases
- AI score
- 60
官方公布了延迟、准确率等具体指标和主要功能,读者可据此评估其是否适合语音智能体等实时场景。
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: ElevenLabs releases Scribe v2 Realtime speech-to-text model. November 11, 2025. https://new.nat6.net/en/news/tw03raba3u8bdx8qwzf02hnx0/