VibeVoice

Turn Text Into Conversations, for Free

VibeVoice.cc brings cutting-edge speech synthesis technology directly to your browser. No downloads, no setup, no credit card — just paste your script and instantly generate natural, multi-speaker audio. Whether you’re experimenting with dialogue, creating voice content, or simply curious about next-generation TTS, it’s completely free to try.

Long-Form and Multi-Speaker by Design

Unlike typical text-to-speech services that are limited to short clips or single voices, VibeVoice.cc supports up to 90 minutes of continuous audio and up to four distinct speakers. This makes it perfect for podcast-style conversations, audiobooks with multiple characters, or interactive storytelling.

Powered by Microsoft Research

Behind the scenes, VibeVoice.cc runs on the open-source VibeVoice framework, developed by Microsoft Research. It combines a large language model with an efficient diffusion-based speech generator, producing high-quality voices that capture realistic tone, pacing, and consistency across long dialogues.

Free, Accessible, and Open

VibeVoice.cc is 100% free to use online. For developers and researchers, the code, models, and documentation are also available under the MIT License, so you can run it locally, extend its capabilities, or integrate it into your own projects.