DevelopmentSources: 1 independent source
ElevenLabs released Eleven v4 speech model
ElevenLabs has released Eleven v4, an updated speech model that improves voice consistency over long productions and responds more accurately to emotional cues like whispering and laughter. The release includes a Turbo variant featuring a 150-millisecond latency for real-time voice agents. Claims are as reported; this summary makes no determination about accuracy or significance.
- Moderate confidence
- Limited corroboration
Coverage
- ElevenLabs' new v4 speech model makes AI voices more expressive and consistentThe Decoder · Independent reporting ·