At ElevenLabs our research is focused on solving human-technology interaction. Eleven v4 is built on a new architecture to generate speech with the intended tone, pacing, emotion, and character.
Eleven v4 Turbo is the low latency version of Eleven v4 with a median inference latency of ~100 ms, built for realtime use cases. Eleven v4 Turbo will power even more personal customer experiences across support, sales, scheduling, and more.
With both models, voice cloning is more authentic, powerful and consistent. Instant Voice Clones now capture voices with extraordinary fidelity from just 10 seconds of audio, while Professional Voice Clones offer our highest fidelity.
For long-form creation, Eleven v4 preserves Direct the performance of Eleven v4 with inline tags. Creators can specify delivery, emotion, pacing, reactions, SFX, style, or simply describe how a line should be delivered and Eleven v4 stages the scene and performs it with naturalness and precision.
Building expressive speech across languages remains one of the hardest challenges in audio AI. Eleven v4 and Eleven v4 Turbo ensure enterprises and their agents can speak to their global audience, natively. With coverage across 90+ languages, including Cantonese, Mongolian and
Eleven v4 gives developers significantly more control over dialogue and pronunciation with IPA support.
While more natural multi-speaker dynamics make conversations feel realistic, responsive, and engaging.
For the next two weeks, we’re making it even easier to try out Eleven v4 and Eleven v4 Turbo.
The Eleven v4 API is discounted to $22 and Eleven v4 Turbo API to $11 per 1M characters and Eleven v4 is free for Creator+ plans in ElevenCreative, up to 2x your monthly credits.
These models are the culmination of our latest research in expressive speech generation, built for any content where delivery matters as much as the words, from character performances through to conversational agents. Available now in ElevenAgents, ElevenCreative and ElevenAPI.