Découvrez Eleven Music. Créez la chanson parfaite pour chaque moment.

Eleven v3 (alpha), now available in the API

20 août 2025 • 2 minutes de lecture

Eleven v3 (alpha), the most expressive text to speech model, is now available in the API for every developer.

Contact Sales Prompting v3 Read the docs

Today, we’re making Eleven v3 (alpha) available in our API.

Eleven v3 (alpha) introduces a new level of expressiveness, control, and multilingual support for building voice-first applications.

Dialogue mode with unlimited speakers
Support for more than 70 languages
Enhanced voice and emotional control using audio tags

These features enable developers to create lifelike, emotionally rich speech experiences for any use case. With dialogue mode, Eleven v3 (alpha) can generate realistic multi-speaker conversations that handle interruptions, shifts in tone, and emotional cues based on context.

If you’re building in media & entertainment, on videos, video games, audiobooks, or media tools - this unlocks a new level of expressiveness.

Already powering industry leaders

Au cours des dernières semaines, nous avons collaboré avec des entreprises de premier plan, comme HeyGen, Poe (par Quora), Captions et InVideo pour intégrer Eleven v3 (alpha) dans leurs produits.

Innovative companies can give their users more engaging content. Like HeyGen who’s using Eleven v3 (alpha) to enhance Avatar video production workflows with dynamic, multilingual voice generation.

ElevenLabs’ models continue to be the most used audio generation model on Poe (by Quora). Now, Poe’s speak button will use ElevenLabs v3 to transform text responses into audio.

Captions is integrating Eleven v3 (alpha) into their AI video platform, Mirage Studio, giving marketers and teams the ability to generate actors with equally dynamic and expressive voices.

Hear v3 (alpha) for yourself

We're off under the lights here for this semi-final clash, the stadium buzzing with anticipation. ElevenLabs United in their iconic black and white shirts, pushing forward with intent straight from the opening whistle. excited The ball is zipped out wide, early attack here. Driving down the wing, pace to Bernie, shouting skips past one, skips past two! Oh, this is beautiful. One-on-one with the full-back, cuts inside—oh, that's a lovely bit of footwork!!! PURE MAGIC on the pitch! ElevenLabs on top form tonight!

Oh my God. laughs You guys, like no joke, I just tried this TTS thing and it was, like, weirdly emotional. Like it literally said, "Hi," and I was, like, on the verge of tears. laughs I don't even cry, okay? I'm a Capricorn.

Get started today

Commencez dès aujourd'hui

Read the docs: https://elevenlabs.io/docs/models#eleven-v3-alpha
Use the Text to Dialogue API: https://elevenlabs.io/docs/capabilities/text-to-dialogue
Get started with our prompting guide: https://elevenlabs.io/docs/best-practices/prompting/eleven-v3

Découvrez les articles de l'équipe ElevenLabs

Safety

Safety

Safety framework for AI voice agents

AI voice agents are increasingly being used in customer service, entertainment, and enterprise applications. With this shift comes the need for clear safeguards to ensure responsible use.

Product

Product

How we engineered RAG to be 50% faster

Tips from latency-sensitive RAG systems in production

Créez avec l'audio AI de la plus haute qualité.

Se lancer gratuitement

Vous avez déjà un compte ? Se connecter