3.2K followers
The most realistic text to speech and voice cloning software. The most compelling, rich, and lifelike voices for creators and publishers seeking the ultimate tools for storytelling.
Launched on June 25th, 2025
Hi Everyone!
Solving AI audio end-to-end means tackling both generation and understanding - from text-to-speech to speech-to-text and everything in between. At ElevenLabs, we re working on breakthroughs in AI audio that bridge research and real-world use.
Ask me anything about what we re building, the challenges of scaling AI speech models, and where this space is headed. Also keen to hear what you ve built with ElevenLabs!
I was making a demo video for my product. For the voice-over, I was using ElevenLabs. My brand name is "LeanAI," but the AI speaker called it "le nee." Is there any option to change the pronunciation of such words?
Well, I tried to find an Australian accent or provide my own and wasn't able to. I was hoping this would be possible.
I've tried it, and the quality of the voices is extremely good. I have a problem, though, and would love to get some help from the ElevenLabs team. In the context I have (Touring, you can find it here on PH) I will most certainly have to deal with numbers, dates etc etc. I've played around on your landing page and tried sentences like "I have 200000 apples", or - in Italian - "Ho 1234 case in giro per il mondo" ("I have 1234 houses around the world"), and the quality of the voice goes down dramatically. In the 200000 apples case, I even got "I have 20 thousand thousand" instead of "I have 2 hundred thousands". Can you help? Perhaps this is something the team should focus on improving? In my case, unfortunately, it makes the tool unusable even though I love the quality of your voices. Thanks!
Hey Hunters,
I am happy to hunt Voice Design v3 from ElevenLabs. They are growing quickly. 😍
Create any voice you can imagine with a prompt.
Try Voice Design v3 → https://elevenlabs.io/voice-design
We’ve rebuilt the underlying Voice Design model to deliver higher quality and broader expressive range.
Generate production-ready voices in 70+ languages with support for hundreds of localized accents.
What’s new in Voice Design v3
• Finer control over character prosody & personality – tone, pacing, inflections, age, and gender
• Compatible with Eleven v3 and expressive [audio tags]
• Increased support for 70+ languages
• Improved accent handling
• Higher audio quality
Voice Design v3 is available to all users.
Share your feedback and view.