VibeVoice is a Hugging Face Space that converts typed or pasted conversation scripts into realistic podcast audio. Users select up to four distinct speaker voices and configure options before generating a single audio file that mimics a real conversation. It leverages voice synthesis models to produce natural intonation and speaker differentiation. The tool is useful for creators who want to prototype or generate dialogue-driven audio content quickly.
VibeVoice is an AI & ML product. It focuses on creating natural-sounding multi-voice audio conversations from text scripts without recording real speakers. VibeVoice is an open-source project aimed at content creators and podcasters. The product is available for free. VibeVoice is available on the web, and it can be self-hosted.
It is developed by yasserrmd, and the product first shipped in 2024. Among its 3 catalogued features are Script Input, Multi-speaker Voices, and Podcast Generation.
Latest indexed changes and source events
yasserrmd/VibeVoice verified by the PulseGate indexer
Other apps tracked under the same category.
