Elevenlabs releases two new text-to-speech models
The story so far
Elevenlabs has released two new speech-to-speech models designed for real-time AI dialogue, Eleven Realtime. Its Max version scored 98.8% on the Big Bench Audio benchmark test with a response time of 0.57 seconds. According to Elevenlabs, no other model currently surpasses it in both speed and accuracy. These models are provided through the ElevenAgents platform and the OpenAI-compatible Realtime API, charged per minute with additional token costs, where v1 Max is priced higher than v1 Mini.
AI-written from the reports · Updated 27 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- The DecoderElevenlabs releases two new speech-to-speech models designed for real-time AI conversations
Elevenlabs has released two new text-to-speech models, Eleven Realtime, with the Max version scoring 98.8% on the Big Bench Audio benchmark test and a response time of 0.57 seconds.