1. Tutorial Introduction

MiMo-Audio is an end-to-end speech model released by Xiaomi in September 2025. Its pre-training data has been expanded to over 100 million hours, and researchers have observed its few-shot learning capabilities across various audio tasks. The team systematically evaluated these capabilities, finding that MiMo-Audio-7B-Base achieved state-of-the-art (SOTA) performance in both open-source model speech intelligence and audio understanding benchmarks. In addition to standard metrics, the model can generalize to tasks not covered in the training data, such as speech conversion, style transfer, and speech editing. Furthermore, MiMo-Audio-7B-Base possesses powerful speech continuation capabilities, generating highly realistic talk show, recitation, live streaming, and debate content. In the post-training phase, researchers compiled a diverse set of instruction fine-tuning corpora and introduced thought mechanisms into audio understanding and generation. The resulting MiMo-Audio-7B-Instruct achieved state-of-the-art performance in open-source benchmarks for audio understanding, spoken dialogue, and instruction-TTS, and in some scenarios, it approached or surpassed closed-source models. The relevant research results are MiMo-Audio-Technical-Report .

This tutorial uses a single RTX 5090 graphics card as computing resource.

2. Effect Examples

1. 🔊 Audio Understanding

2. 🎵 Audio Generation Text-to-Speech

3. 🎤 Spoken Dialogue

4. 💬 S2T Dialogue

5. 📝 Text-to-Text Dialogue

3. Operation steps

1. Start the container

2. Initialize weight parameters

If "Bad Gateway" is displayed, it means the model is initializing. Since the model is large, please wait about 2-3 minutes and refresh the page.

When using the Safari browser, the audio may not be played directly and needs to be downloaded before playing.

3. Audio Understanding

4. Audio Generation

5. Voice Conversation

6. Voice-to-text conversation

7. Text-to-text conversation

Citation Information

@misc{coreteam2025mimoaudio,
      title={MiMo-Audio: Audio Language Models are Few-Shot Learners}, 
      author={LLM-Core-Team Xiaomi},
      year={2025},
      url={https://github.com/XiaomiMiMo/MiMo-Audio}, 
}