AI & RoboticsMore in AI & Robotics→
ElevenLabs' Eleven v4 Speech Model Sharpens Expressiveness and Voice Consistency
Key Takeaways
- ElevenLabs released Eleven v4, a speech model that follows direction cues more accurately and keeps voices consistent across long productions.
- The model generates laughter, whispers, and sound effects like slamming doors more reliably than v3, with more dependable pronunciation controls.
- A new architecture analyzes a script's tone, pacing, and context, helping narrators and characters stay stable even when individual lines are regenerated.
- Eleven v4 handles up to 10,000 characters per request — roughly ten minutes of audio — and supports more than 90 languages, up from about 70.
DE
DT Editorial Team··via the-decoder.com