# Xiaomi's MiMo-Audio 7B Tackles Complex Speech Tasks

> This new instruction-tuned model from Xiaomi can handle a flexible combination of audio and text inputs and outputs, from transcription to voice synthesis.

Published by The Open Weights on Sep 18, 2025. Canonical: https://theopenweights.com/news/mimo-audio-7b-udzb

## Key facts

- Company: Xiaomi
- Model: MiMo-Audio-7B-Instruct
- Version: 7B-Instruct
- Category: Any-to-Any
- Modalities: Any-to-Any, Text → Speech, Speech → Text
- License: MIT (Open weights, commercial use allowed)
- Parameters: 7B
- Context window: 8K tokens
- Architecture: MiMoAudioModel
- Precision: BF16
- Weights size: 16 GB
- Significance: notable
- Published: 2025-09-18
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/XiaomiMiMo/MiMo-Audio-7B-Instruct
- Canonical URL: https://theopenweights.com/news/mimo-audio-7b-udzb

Xiaomi has released MiMo-Audio-7B-Instruct, a versatile 7-billion-parameter model designed to handle a wide array of speech and audio tasks. Published under a permissive MIT license, the model marks a notable open-source contribution from the major electronics company, providing a powerful new tool for developers working with audio AI.

The key innovation of MiMo-Audio is its "any-to-any" architecture. Unlike specialized models that perform a single function, MiMo-Audio is a generalist system that can process and generate audio and text in flexible combinations. This allows it to act as a unified solution for multiple distinct tasks.

## A Unified Model for Speech AI

According to its [release materials on Hugging Face](https://huggingface.co/XiaomiMiMo/MiMo-Audio-7B-Instruct), the instruction-tuned model is capable of performing a variety of functions, including:

*   **Speech Recognition (ASR):** Transcribing spoken audio to text.
*   **Text-to-Speech (TTS):** Synthesizing speech from written text.
*   **Speech-to-Speech Translation (S2ST):** Translating spoken language directly into another spoken language.
*   **Audio Captioning and Generation:** Describing sounds or creating audio from text prompts.

This flexibility makes MiMo-Audio a compelling foundation for building complex voice-enabled applications. By releasing a capable, general-purpose audio model under an open license, Xiaomi is providing a significant building block for the open-source AI community and a strong alternative to proprietary speech APIs.

## Get the model

- [Hugging Face](https://huggingface.co/XiaomiMiMo/MiMo-Audio-7B-Instruct)

## Sources

- [XiaomiMiMo/MiMo-Audio-7B-Instruct](https://huggingface.co/XiaomiMiMo/MiMo-Audio-7B-Instruct) — Hugging Face, Sep 18, 2025

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Xiaomi's MiMo-Audio 7B Tackles Complex Speech Tasks", The Open Weights, Sep 18, 2025, https://theopenweights.com/news/mimo-audio-7b-udzb