Release announced
Released on Sep 28, 2026
ElevenLabs announced this model on 2026-09-28. Languages: more than 90 languages.
- Hosting route
- First-party API
- Affected scope
- Languages: more than 90 languages
- Announced
- Sep 28, 2026
- First seen by ModelClock
- Oct 3, 2026
What the provider published
elevenlabs.io ↗Eleven v4 and Eleven v4 Turbo
Eleven v4 and Eleven v4 Turbo are now available. Eleven v4 provides higher-quality, more expressive speech and improved voice cloning across more than 90 languages. Eleven v4 Turbo provides the same model family for real-time applications, with median inference latency of approximately 100 ms.
Use
eleven_v4through the Text to Dialogue API for content creation and long-form audio. Useeleven_v4_turbothrough the Text to Dialogue WebSocket for agents and interactive applications.
Read from the provider's text; the quote is the provider's exact lines.