VibeVoice

VibeVoice — Open-source AI for expressive, long-form multi-speaker voice generation

Explore VibeVoice at https://www.vibevoiceai.com — 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.

Screenshots

Own VibeVoice? Claim it to unlock editing, a ✓ Verified badge, and replies to reviews.

Reviews

No reviews yet — be the first to review this tool.

Similar tools

More Audio tools →

AdVuAudio

AdVu is an AI-powered marketing intelligence platform that unifies advertising, analytics, and ecommerce data in one dashboard, helping marketers monitor performance, generate actionable insights, cre

Paid

musegenAudio

AI Music Generator for Commercial Songs from Text, Audio, or Lyrics

Freemium

Best Donald Trump Text to SpeechAudio

Infinite Talk AI does not provide or endorse exact replicas of any real person’s voice.

CaptionixAudio

Easily convert audio to text-effortlessly and accurately

NonoisyAudio

Nonoisy simplifies audio post-production by streamlining intricate editing tasks into easy-to-follow steps, ensuring a user-friendly experience for even the most novice users.

Drayk ItAudio

Drayk is an AI-powered system that creates uniquely personalized Drake songs for your music playlist by incorporating user inputs.