christian.schwarz/VibeVoice
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

restructure README

Browse Source
This commit is contained in:
YaoyaoChang
2026-01-22 00:26:54 -08:00
parent ce90a49960
commit 32a7040ce0
5 changed files with 247 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+81 -38
View File
@@ -21,58 +21,85 @@
<h3>📰 News</h3>
<strong>2026-01-21: 📣 We open-sourced <a href="docs/vibevoice-asr.md"><strong>VibeVoice-ASR</strong></a>, a unified speech-to-text model designed to handle 60-minute long-form audio in a single pass, generating structured transcriptions containing Who (Speaker), When (Timestamps), and What (Content), with support for User-Customized Context. [Try it.](https://aka.ms/vibevoice-asr)</strong>
<strong>2026-01-21: 📣 We open-sourced <a href="docs/vibevoice-asr.md"><strong>VibeVoice-ASR</strong></a>, a unified speech-to-text model designed to handle 60-minute long-form audio in a single pass, generating structured transcriptions containing Who (Speaker), When (Timestamps), and What (Content), with support for User-Customized Context. Try it in [Playground](https://aka.ms/vibevoice-asr)</strong>.
https://github.com/user-attachments/assets/acde5602-dc17-4314-9e3b-c630bc84aefa
<p align="center">
<img src="Figures/DER.jpg" alt="DER" height="200">
<img src="Figures/cpWER.jpg" alt="cpWER" height="200">
<img src="Figures/tcpWER.jpg" alt="tcpWER" height="200">
</p>
2025-12-16: 📣 We added more experimental speakers for exploration, including multilingual voices and 11 distinct English style voices. [Try it](docs/vibevoice-realtime-0.5b.md#optional-more-experimental-voices). More speaker types will be added over time.
2025-12-09: 📣 We added experimental speakers in nine languages (DE, FR, IT, JP, KR, NL, PL, PT, ES) for exploration—welcome to try them out and share your feedback.
2025-12-16: 📣 We added experimental speakers to <a href="docs/vibevoice-realtime-0.5b.md"><strong>VibeVoice‑Realtime‑0.5B</strong></a> for exploration, including multilingual voices in nine languages (DE, FR, IT, JP, KR, NL, PL, PT, ES) and 11 distinct English style voices. [Try it](docs/vibevoice-realtime-0.5b.md#optional-more-experimental-voices). More speaker types will be added over time.
2025-12-03: 📣 We open-sourced <a href="docs/vibevoice-realtime-0.5b.md"><strong>VibeVoice‑Realtime‑0.5B</strong></a>, a real‑time text‑to‑speech model that supports streaming text input and robust long-form speech generation. Try it on [Colab](https://colab.research.google.com/github/microsoft/VibeVoice/blob/main/demo/vibevoice_realtime_colab.ipynb).
To mitigate deepfake risks and ensure low latency for the first speech chunk, voice prompts are provided in an embedded format. For users requiring voice customization, please reach out to our team. We will also be expanding the range of available speakers.
<br>
https://github.com/user-attachments/assets/0901d274-f6ae-46ef-a0fd-3c4fba4f76dc
2025-09-05: VibeVoice is an open-source research framework intended to advance collaboration in the speech synthesis community. After release, we discovered instances where the tool was used in ways inconsistent with the stated intent. Since responsible use of AI is one of Microsoft’s guiding principles, we have removed the VibeVoice-TTS code from this repository.
> (Launch your own realtime demo via the websocket example in [Usage](docs/vibevoice-realtime-0.5b.md#usage-1-launch-real-time-websocket-demo)).
2025-08-25: 📣 We open-sourced <a href="docs/vibevoice-tts.md"><strong>VibeVoice-TTS</strong></a>, a long-form multi-speaker text-to-speech model that can synthesize speech up to 90 minutes long with up to 4 distinct speakers.
</div>
2025-09-05: VibeVoice is an open-source research framework intended to advance collaboration in the speech synthesis community. After release, we discovered instances where the tool was used in ways inconsistent with the stated intent. Since responsible use of AI is one of Microsoft’s guiding principles, we have disabled this repo until we are confident that out-of-scope use is no longer possible.
## Overview
VibeVoice is a **family of open-source frontier voice AI models** that includes both Text-to-Speech (TTS) and Automatic Speech Recognition (ASR) models.
A core innovation of VibeVoice is its use of continuous speech tokenizers (Acoustic and Semantic) operating at an ultra-low frame rate of **7.5 Hz**. These tokenizers efficiently preserve audio fidelity while significantly boosting computational efficiency for processing long sequences. VibeVoice employs a [next-token diffusion](https://arxiv.org/abs/2412.08635) framework, leveraging a Large Language Model (LLM) to understand textual context and dialogue flow, and a diffusion head to generate high-fidelity acoustic details.
For more information, demos, and examples, please visit our [Project Page](https://microsoft.github.io/VibeVoice).
### Overview
<div align="center">
VibeVoice is a novel framework designed for generating **expressive**, **long-form**, **multi-speaker** conversational audio, such as podcasts, from text. It addresses significant challenges in traditional Text-to-Speech (TTS) systems, particularly in scalability, speaker consistency, and natural turn-taking.
| Model | Weight | Quick Try |
|-------|--------------|---------|
| VibeVoice-TTS-1.5B | [HF Link](https://huggingface.co/microsoft/VibeVoice-1.5B) | Disabled |
| VibeVoice-Realtime-0.5B | [HF Link](https://huggingface.co/microsoft/VibeVoice-Realtime-0.5B) | [Colab](https://colab.research.google.com/github/microsoft/VibeVoice/blob/main/demo/vibevoice_realtime_colab.ipynb) |
| VibeVoice-ASR-7B | [HF Link](https://huggingface.co/microsoft/VibeVoice-ASR) | [Playground](https://aka.ms/vibevoice-asr) |
VibeVoice currently includes two model variants:
</div>
- **Long-form multi-speaker model**: Synthesizes conversational/single-speaker speech up to **90 minutes** with up to **4 distinct speakers**, surpassing the typical 1–2 speaker limits of many prior models.
- **[Realtime streaming TTS model](docs/vibevoice-realtime-0.5b.md)**: Produces initial audible speech in ~**300 ms** and supports **streaming text input** for single-speaker **real-time** speech generation; designed for low-latency generation.
A core innovation of VibeVoice is its use of continuous speech tokenizers (Acoustic and Semantic) operating at an ultra-low frame rate of 7.5 Hz. These tokenizers efficiently preserve audio fidelity while significantly boosting computational efficiency for processing long sequences. VibeVoice employs a [next-token diffusion](https://arxiv.org/abs/2412.08635) framework, leveraging a Large Language Model (LLM) to understand textual context and dialogue flow, and a diffusion head to generate high-fidelity acoustic details.
## Models
<p align="left">
<img src="Figures/MOS-preference.png" alt="MOS Preference Results" height="260px">
<img src="Figures/VibeVoice.jpg" alt="VibeVoice Overview" height="250px" style="margin-right: 10px;">
</p>
### 1. 📖 [VibeVoice-ASR](docs/vibevoice-asr.md) - Long-form Speech Recognition
**VibeVoice-ASR** is a unified speech-to-text model designed to handle **60-minute long-form audio** in a single pass, generating structured transcriptions containing **Who (Speaker), When (Timestamps), and What (Content)**, with support for **Customized Hotwords**.
- **🕒 60-minute Single-Pass Processing**:
Unlike conventional ASR models that slice audio into short chunks (often losing global context), VibeVoice ASR accepts up to **60 minutes** of continuous audio input within 64K token length. This ensures consistent speaker tracking and semantic coherence across the entire hour.
- **👤 Customized Hotwords**:
Users can provide customized hotwords (e.g., specific names, technical terms, or background info) to guide the recognition process, significantly improving accuracy on domain-specific content.
- **📝 Rich Transcription (Who, When, What)**:
The model jointly performs ASR, diarization, and timestamping, producing a structured output that indicates *who* said *what* and *when*.
[📖 Documentation](docs/vibevoice-asr.md) | [🤗 Hugging Face](https://huggingface.co/microsoft/VibeVoice-ASR) | [🎮 Playground](https://aka.ms/vibevoice-asr)
### 🎵 Demo Examples
<div align="center" id="vibevoice-asr">
https://github.com/user-attachments/assets/acde5602-dc17-4314-9e3b-c630bc84aefa
</div>
**Video Demo**
### 2. 🎙️ [VibeVoice-TTS](docs/vibevoice-tts.md) - Long-form Multi-speaker TTS
**Best for**: Long-form conversational audio, podcasts, multi-speaker dialogues
- **⏱️ 90-minute Long-form Generation**:
Synthesizes conversational/single-speaker speech up to **90 minutes** in a single pass, maintaining speaker consistency and semantic coherence throughout.
- **👥 Multi-speaker Support**:
Supports up to **4 distinct speakers** in a single conversation, with natural turn-taking and speaker consistency across long dialogues.
- **🎭 Expressive Speech**:
Generates expressive, natural-sounding speech that captures conversational dynamics and emotional nuances.
- **🌐 Multi-lingual Support**:
Supports English, Chinese and other languages.
[📖 Documentation](docs/vibevoice-tts.md) | [🤗 Hugging Face](https://huggingface.co/microsoft/VibeVoice-1.5B) | [📊 Paper](https://arxiv.org/pdf/2508.19205)
We produced this video with [Wan2.2](https://github.com/Wan-Video/Wan2.2). We sincerely appreciate the Wan-Video team for their great work.
**English**
<div align="center">
@@ -111,20 +138,36 @@ https://github.com/user-attachments/assets/a357c4b6-9768-495c-a576-1618f6275727
</div>
For more examples, see the [Project Page](https://microsoft.github.io/VibeVoice).
## Risks and limitations
### 3. ⚡ [VibeVoice-Streaming](docs/vibevoice-realtime-0.5b.md) - Real-time Streaming TTS
VibeVoice-Realtime is a **lightweight real‑time** text-to-speech model supporting **streaming text input** and **robust long-form speech generation**.
- Parameter size: 0.5B (deployment-friendly)
- Real-time TTS (~300 milliseconds first audible latency)
- Streaming text input
- Robust long-form speech generation (~10 minutes)
[📖 Documentation](docs/vibevoice-realtime-0.5b.md) | [🤗 Hugging Face](https://huggingface.co/microsoft/VibeVoice-Realtime-0.5B) | [🚀 Colab](https://colab.research.google.com/github/microsoft/VibeVoice/blob/main/demo/vibevoice_realtime_colab.ipynb)
<div align="center" id="generated-example-audio-vibevoice-realtime">
https://github.com/user-attachments/assets/0901d274-f6ae-46ef-a0fd-3c4fba4f76dc
</div>
## ⚠️ Risks and Limitations
While efforts have been made to optimize it through various techniques, it may still produce outputs that are unexpected, biased, or inaccurate. VibeVoice inherits any biases, errors, or omissions produced by its base model (specifically, Qwen2.5 1.5b in this release).
Potential for Deepfakes and Disinformation: High-quality synthetic speech can be misused to create convincing fake audio content for impersonation, fraud, or spreading disinformation. Users must ensure transcripts are reliable, check content accuracy, and avoid using generated content in misleading ways. Users are expected to use the generated content and to deploy the models in a lawful manner, in full compliance with all applicable laws and regulations in the relevant jurisdictions. It is best practice to disclose the use of AI when sharing AI-generated content.
English and Chinese only: Transcripts in languages other than English or Chinese may result in unexpected audio outputs.
Non-Speech Audio: The model focuses solely on speech synthesis and does not handle background noise, music, or other sound effects.
Overlapping Speech: The current model does not explicitly model or generate overlapping speech segments in conversations.
We do not recommend using VibeVoice in commercial or real-world applications without further testing and development. This model is intended for research and development purposes only. Please use responsibly.