微软开源了一个语音 AI，60 分钟长音频一次转写，4 个人同时说话都能搞定

VibeVoice，微软开源，24.8k star，今天才知道这个。录音一键转文字这件事，我之前一直用 Whisper，但它处理长会议录音经常超时，多人说话识别错得也挺厉害的。

VibeVoice 这个直接支持 60 分钟连续音频，自带说话人分离和时间戳，四个人同时说话的场景也能分清楚谁说了什么。最让我意外的是 TTS 这边，4 个角色同时合成，90 分钟连贯输出，声音全程不跑偏。

想做有声书或者播客内容的同学应该会很感兴趣，以前多角色合成经常前后声音不一致，这个解决了。底层是 Qwen2.5 加了专门的连续语音 tokenizer，还有个 0.5B 的轻量版本，300ms 延迟，可以直接接进对话 AI 做实时语音交互，不用再单独接第三方 TTS 服务了。

正在想把 ASR 这块接进自己的会议记录工具里，如果真能稳定跑，一个会下来自动生成带发言人标注的纪要，那效率真的拉满了。

开源地址： https://github.com/microsoft/VibeVoice…

#AI #AIAgent

microsoft/VibeVoice

Source: https://github.com/microsoft/VibeVoice

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 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.

Models

1. 📖 VibeVoice-ASR - 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 | 🤗 Hugging Face | 🎮 Playground | 🛠️ Finetuning | 📊 Paper

2. 🎙️ VibeVoice-TTS - 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 | 🤗 Hugging Face | 📊 Paper

English

Chinese

Cross-Lingual

Spontaneous Singing

Long Conversation with 4 people

3. ⚡ VibeVoice-Streaming - 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 | 🤗 Hugging Face | 🚀 Colab

Contributing

Please see CONTRIBUTING.md for detailed contribution guidelines.

⚠️ 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.

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.

Star History