ElevenLabs releases Scribe v3 speech-to-text models
What happened
On November 12, The Decoder reported that ElevenLabs released two speech-to-text models, Scribe v3 and Scribe v3 Live, aimed at recording transcription and real-time applications respectively. The release splits recording processing from live voice interaction. Scribe v3 Live uses conversation context to judge whether a speaker has finished talking, rather than only transcribing speech. That capability is meant to reduce voice agents cutting in before a caller has finished, the main feature of the live version as described in the report.
Written by AI from the coverage · updated 4 days ago
Coverage
Follow the reports to see the story from different sides.
- The DecoderElevenLabs Scribe v3 Live uses conversational context to stop voice agents from cutting off callers mid-sentence
ElevenLabs 发布 Scribe v3 和 Scribe v3 Live 语音转文字模型,分别面向录音与实时应用,后者结合对话上下文判断说话者是否结束发言。
Heat over time
Heat now 3·Comparable peak 10(Nov 12 23:00)·Comparable change over 24 hours -49%
The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.