VibeVoice

An open source AI for speech generation

6 followers

An open source AI for speech generation

6 followers

an open-source TTS platform based on Microsoft’s VibeVoice model. Generate realistic, multi-speaker audio—up to 90 minutes in one go—in English or Chinese, with expressive style and research-friendly MIT licensing.

Free

Launch tags:Design Tools•Marketing•Tech

Launch Team

Auth0 — Start building with Auth0 for AI Agents, now generally available.

Start building with Auth0 for AI Agents, now generally available.

Promoted

Maker

📌

Hey Product Hunt, We’re excited to introduce VibeVoice at https://www.vibevoiceai.com/ — built on Microsoft’s open-source VibeVoice model. With it, you can: •Generate long (up to 90 min), expressive, multi-speaker voice audio •Support both English and Chinese, with cross-lingual and even simple singing capabilities •Rely on an MIT-licensed, research-oriented framework powered by tokenizers and diffusion-based generation We believe VibeVoice offers a unique blend of quality, flexibility, and ethical openness. Give it a spin and let us know what you build!

Report

6mo ago

So as a single payment, USD$99 buys 4800credits and the rate is 4credits per minute?
Where can I purchase the credits and are they then automatically applied to my account?
Where can I explore all the available voices and how many voices are there?
Please clarify the procedure for creating a voice-clone?
I may have missed it but can the speed and pitch of the voices be adjusted?

Thanks, it looks simple and that's great!!

Report

6mo ago