Just experienced something mind-blowing! ElevenLabs has dropped v3 (alpha), and it's a game-changer in AI voice tech. The expressiveness is unreal—whispers, dramatic tones, even Shakespeare!s.

For those curious about the tech, Eleven v3 supports 70+ languages, multi-speaker dialogues, and audio tags like [excited], [whispers], [laughs]. It's not just reading text; it's performing it! This model understands context deeply, making conversations feel spontaneous.

Heads up! Eleven v3 is 80% off this June, so now's the perfect time to dive in. Whether you're into gaming, audiobooks, or just love tech, this is your chance to explore the future of voice. What's the first thing you'd create with it? Share your ideas!

The new architecture of Eleven v3 deeply understands text - 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]

Create multi-speaker dialogue that feels authentic and natural. Eleven v3 captures interruptions, tone changes, and emotional nuances driven by the conversation's context.

You can now generate full conversations. With tone shifts. Emotional nuance. Natural flow. 🎧 Listen to the demos : @elevenlabsio 🔥 Try it in alpha (80% off this month)

That's a wrap! If you enjoyed this thread: 1. Follow me and @shedntcare_ for more of these 2. Like and RT the tweet below to share this thread with your audience

Wow, great update

Awesome !

Great job

This just raised the bar for AI voice. The emotional range is unreal—feels like you're listening to a real human, not a script, Must-try