ElevenLabs launches Scribe v3 speech-to-text models
ElevenLabs released Scribe v3 for prerecorded audio and Scribe v3 Live for low-latency real-time transcription, with both models available through ElevenAPI and ElevenAgents. Artificial Analysis ranked Scribe v3 among the most accurate transcription models but found it slower and more expensive than several rivals; its benchmark did not test real-time performance, speaker diarization, or rare-language accuracy.
The release gives developers high-accuracy transcription options for both recorded and live workflows, while independent testing shows a clear tradeoff between recognition accuracy, speed, and price.
ElevenLabs Scribe v3 Live uses conversational context to stop voice agents from cutting off callers mid-sentence
Maximilian Schreiner View the LinkedIn Profile of Maximilian Schreiner
Nov 12, 2026

GPT-Image-2 prompted by THE DECODER
Key Points
- Elevenlabs has released Scribe v3 and Scribe v3 Live, two speech recognition models built for messy audio situations like crosstalk and background noise, covering both pre-recorded files and real-time use.
- Benchmarks from Artificial Analysis put Scribe v3 among the most accurate transcription models on the market, but it runs slower and costs more than rival models from Microsoft and xAI.
- The real-time version analyzes conversational context to avoid cutting callers off during brief pauses, and ElevenLabs is expanding enterprise partnerships with Nvidia and McKinsey.
#ElevenLabs#Scribe v3#Scribe v3 Live#ElevenAPI#ElevenAgents#Artificial Analysis