# VibeVoice

> Microsoft's open voice AI models

Open-source models for expressive, long-form speech generation and recognition.

- Source: https://github.com/microsoft/VibeVoice
- Homepage: https://microsoft.github.io/VibeVoice/
- License: MIT
- Language: Python
- Stars: 54603
- Forks: 6140
- Contributors: 22
- Last commit: 2026-09-03
- Purpose: AI & LLM tooling, Media & photos
- Runs on: Library / SDK
- For: Personal, Enterprise

## Worth score: 71/100

How much DigGitHub recommends it, from activity, adoption, docs, license and security signals.

- Popularity: 24/25
- Momentum: 10/20
- Maintenance: 15/25
- Community: 11/15
- Readiness: 11/15

## Alternatives

- [FunASR](https://diggithub.com/modelscope/FunASR.md): Speech recognition toolkit
- [whisper.cpp](https://diggithub.com/ggml-org/whisper.cpp.md): Whisper speech recognition in C/C++
- [HyperFrames](https://diggithub.com/heygen-com/hyperframes.md): Write HTML, render video
- [VoxCPM](https://diggithub.com/OpenBMB/VoxCPM.md): Tokenizer-free multilingual TTS
- [WhisperLiveKit](https://diggithub.com/QuentinFuxa/WhisperLiveKit.md): Real-time local speech-to-text
- [WhisperX](https://diggithub.com/m-bain/whisperX.md): Speech recognition with word timestamps
- [IndexTTS](https://diggithub.com/index-tts/index-tts.md): Controllable zero-shot TTS
- [FastVideo](https://diggithub.com/hao-ai-lab/FastVideo.md): Accelerated video generation

---

Source page: https://diggithub.com/microsoft/VibeVoice
Updated: 2026-10-03