microsoft/VibeVoice

Open-Source Frontier Voice AI

Python53K stars6K forks+219 today

What it does

VibeVoice is an open-source AI framework that includes speech-to-text and text-to-speech models, designed for efficient long-form audio processing with high fidelity. It matters because it advances the state-of-the-art in voice AI technology.

Star history

Not enough history yet — 1 day(s) recorded. The daily snapshot builds this up.

Tracking

Last trending: 2026-06-06

Creator kit

Hook

Revolutionize your audio content creation and processing with VibeVoice, Microsoft's open-source frontier voice AI. 🎤💻 #VibeVoice #Microsoft

Content angles

Creating tutorials on how to use VibeVoice for speech-to-text in long-form audio
Developing a comparison review of VibeVoice against other text-to-speech solutions
Exploring the ethical implications and responsible usage guidelines of VibeVoice

Who should care

AI researchers, developers working with voice technologies, content creators dealing with large audio files