Back to news

AI · Article

ElevenLabs Releases Scribe v3 Speech Recognition With 27% Fewer Word Errors

위런치 ·

At a glance

ElevenLabs has released Scribe v3 and Scribe v3 Live, two speech-to-text models for turning recorded and live speech into text. Both are available through its developer API, and Scribe v3 Live also works inside its ElevenAgents platform for businesses.

Key points

Why it matters

Better speaker separation and real-time turn detection can make call and meeting transcription more accurate, which matters for businesses handling many conversations.

Original source

일레븐랩스, 음성 인식 ‘스크라이브 v3’ 공개…단어 오류 27% 줄였다

위런치 · Nov 19, 08:28 KST

Read on 위런치 ↗

AI summarized the original article. Check the original for accuracy. Copyright belongs to 위런치.

Other coverage

ElevenLabs · Ranking and more news