Eleven v3 (alpha), now available in the API

Last updated Aug 20, 2025 • 3 minutes reading time

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

Learn More Contact Sales Prompting v3 Read the docs

Eleven v3 is no longer in alpha, and is now generally available.

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

Over the past weeks, we partnered with leading companies, like HeyGen, Poe (by Quora), Captions and InVideo to integrate Eleven v3 (alpha) into their products.

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.

InVideo leverages Eleven v3 (alpha) to power its AI-driven video creation platform, enabling users to generate complete videos—including scripts, visuals, voiceovers, subtitles, music and more — in over 70 languages.