ElevenLabs launches Eleven Realtime speech models
Trending storyDeveloping
ElevenLabs launches Eleven Realtime speech models
1 reports1 sourcesUpdated 2 hours ago
What you need to know
AI summary
ElevenLabs released two speech-to-speech models, Eleven Realtime v1 Max and v1 Mini, available through the ElevenAgents platform and an OpenAI-compatible Realtime API. Pricing is per minute plus token costs, with v1 Max costing more than v1 Mini. According to ElevenLabs, v1 Max scores 98.8 percent on the Big Bench Audio benchmark with a 0.57-second response time.
Generated by AI from the reporting · updated 1 hour ago
Latest updateOct 20 19:03
ElevenLabs releases two Eleven Realtime speech-to-speech modelsTimeline
Follow the reports to see every side of the story.
Oct 20
- The DecoderElevenLabs releases two Eleven Realtime speech-to-speech models
ElevenLabs released two speech-to-speech models called Eleven Realtime. The Max variant scores 98.8 percent on the Big Bench Audio benchmark with a 0.57-second response time.
Heat trend for this story
Not enough continuous data yet to chart a trend.