Expressive text-to-speech
Eleven v4 generates speech with emotional range and inline direction for delivery.
Eleven v4 and Eleven v4 Turbo
ElevenLabs' fastest and most emotive voice models yet
The overview
What is Eleven v4 and Eleven v4 Turbo?
Eleven v4 generates expressive speech with control over tone, pacing, emotion and character, while v4 Turbo targets low-latency live applications such as voice agents. The models support multilingual generation, voice cloning and longer narration with consistent speaker identity, and are available through ElevenLabs apps, API and agent products.
Around the internet
What people are saying
Public experiences, questions, and discussions.
No discussions collected yet.
Inside the toolkit
Key features
Real-time Turbo speech
Eleven v4 Turbo provides real-time speech synthesis with about 100 ms median inference latency.
Voice cloning
Eleven v4 supports instant voice cloning from a short sample and Professional Voice Clones.
Voice design and pronunciation controls
Describe a voice to generate it; pronunciation dictionaries define names and technical terms.
Multilingual dialogue and audio tags
The v4 page lists 90+ languages, multiple speakers, sound effects, and inline direction tags.
Where it fits
Use cases
- Produce expressive narrationEleven v4 is positioned for produced content where expressive, high-fidelity output matters.
- Build real-time voice agentsEleven v4 Turbo is described for real-time applications and voice agents through the API.
- Create multilingual dialogueThe models support more than 90 languages; the page says a voice can retain its identity across supported language changes.
Keep exploring
