Eleven v4
Eleven v4 uses a new speech architecture to interpret a script’s tone and context. It supports more than 90 languages and aims to preserve speaker identity across a conversation.
Performance and continuity
The release improves phonetic pronunciation controls, voice cloning and continuity between generated passages. It also supports Professional Voice Clones.ElevenLabs: Eleven v4 and v4 Turbo release
Practical guidance. For a recurring character, review both a long scene and regenerated lines. Consistent identity across these cases matters more than the quality of one isolated sentence.ElevenLabs: Eleven v4 and v4 Turbo release
Specifications & access
| Detail | Value and conditions |
|---|---|
| Launch date | |
| Access | API, Provider product |
| Model identifiers | eleven_v4 |
| Request size | 10,000 characters; this is not a token limitElevenLabs API introduction and model specifications |
| API route | Text to DialogueElevenLabs: September 2026 model and API changes |
Related models
- Eleven v4 Turbo
ElevenLabs · Eleven speech
Low-latency v4 speech model for expressive interactive voices.
Launch date API · Provider product - Eleven v3
ElevenLabs · Eleven speech
Expressive speech model with audio tags and multi-speaker performance.
Launch date API · Provider product - Eleven Multilingual v2
ElevenLabs · Eleven speech
Multilingual speech model for stable long-form narration.
Launch date API · Provider product