herry blog.: Introducing Eleven v3 — the most expressive Text to Speech model.

05 Juni, 2025

Introducing Eleven v3 — the most expressive Text to Speech model.

We're excited to announce the release of Eleven v3 (alpha), the most expressive Text to Speech model. v3 brings unprecedented control and realism to speech generation:

70+ languages
Multi-speaker dialogue
Audio tags like [excited], [whispers], and [sighs]

This is a research preview. It requires more prompt engineering than previous models - but the generations are breathtaking. We'll continue fine-tuning to improve reliability and control.

The new architecture of Eleven v3 understands text at a deeper level - delivering much greater expressiveness. And now you can guide generations more directly using audio tags:

Emotions [sad] [angry] [happily]
Delivery direction [whispers] [shouts]
Non-verbal reactions [laughs] [clears throat] [sighs]

Generate dynamic multi-speaker dialogue that handles interruptions, shifts in tone, and emotional cues based on conversational context.

If you're working on videos, audiobooks, or media tools - this unlocks a new level of expressiveness. For real-time and conversational use cases, we recommend staying with v2.5 Turbo or Flash for now. A real-time version of v3 is in development.

Public API access is coming soon. For early access, please contact sales.

Eleven v3 supports 70+ languages and a variety of tones and accents.

It is available today in the UI with 80% off in June. Try it here https://elevenlabs.io/v3 - make sure to see our v3 prompting best practices - and share your best generations with us.

The ElevenLabs team