ElevenLabs Releases Scribe v3 and Scribe v3 Live Speech Recognition Models
Understand the story
On November 12, 2026, The Decoder reported that ElevenLabs released two speech-to-text models, Scribe v3 and Scribe v3 Live. Scribe v3 targets transcription of pre-recorded audio, while Scribe v3 Live targets low-latency real-time speech recognition, covering offline and real-time use cases respectively. Both models are now available through the ElevenAPI and ElevenAgents platforms, where users can access these capabilities. There are currently no further reports on performance metrics, pricing, or future plans, and the story is still developing.
AI overview of reporting · Updated 2 h前
Reporting timeline
Explore different aspects of the story through its reporting.
- The DecoderElevenLabs Scribe v3 Live uses conversational context to stop voice agents from cutting off callers mid-sentence
ElevenLabs released two speech-to-text models, Scribe v3 and Scribe v3 Live, targeting pre-recorded audio and low-latency real-time scenarios respectively, now available via the ElevenAPI and ElevenAgents platforms.
Story heat trend
Not enough continuous observations to show a trend yet.