Ankit Sharma

Eleven v3 (alpha) - The most expressive Text to Speech model ever

by
Supporting 70+ languages, multi-speaker dialogue, and audio tags such as [excited], [sighs], [laughing], and [whispers]. Now in public alpha and 80% off in June.

Add a comment

Replies

Best
Nabin Islam

This is next-level for content creation! Finally, TTS that doesn't sound robotic - the 'lifelike' claim has me genuinely excited. As a podcaster who struggles with voiceovers, this could be a gamechanger.

Would love to know:

How many voice options/styles are available?

Can we adjust emotional tone (excited, serious, etc.)?

What's the processing time for longer narrations?

The storytelling potential here is massive - from audiobooks to YouTube to e-learning. If the quality matches the promise, this could replace hiring voice actors for many projects.

Any plans for real-time voice conversion? That would be mind-blowing! Congrats on launching what looks like the new gold standard in AI voice tech. #VoiceRevolution"**

[Optional tweak for different tone]:

For more concise: "Game-changing TTS! The 'lifelike' promise solves my biggest pain point with AI voices. When can we test it? #NeedThisNow

Manu Goel

Just in time...this is what we felt was missing when trying it last week....better expression and emotions.

I don't know

@saaswarrior, Chinese speech is not native. If your team accepts Chinese on-ground support, would like to join. Thank you.