An advanced AI-powered text-to-speech skill leveraging the Xiaomi MiMo V2 API to create natural, expressive voices for developers.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install xiaomi-mimo-voice
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install xiaomi-mimo-voice using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Xiaomi MiMo Voice TTS?
Xiaomi MiMo Voice is a sophisticated text-to-speech (TTS) integration designed for the Openclaw Skills ecosystem. By utilizing the Xiaomi MiMo V2 API, it allows developers to convert written text into high-quality, natural-sounding audio. This skill is particularly notable for its deep support for Chinese and English languages, offering a variety of specialized voices optimized for specific linguistic nuances.
Beyond basic synthesis, the tool provides extensive control over the emotional tone and character persona of the generated speech. Whether you need a professional narrator, a specific regional dialect, or an emotionally charged character voice, this addition to your Openclaw Skills library provides the technical flexibility required for modern audio-centric applications.
Xiaomi MiMo Voice TTS Use Cases
- Creating localized voiceovers using specific regional dialects such as Cantonese, Northeastern, or Sichuanese.
- Developing interactive storytelling applications using roleplay voices like Sun Wukong or Zhuge Liang.
- Automating content narration for news or articles using the specialized Narration style.
- Generating multilingual audio assets for global applications in both Chinese and English.
- Enhancing AI agent interactivity within Openclaw Skills by providing expressive, emotional feedback.
How Xiaomi MiMo Voice TTS Works
- The user initiates the skill via a CLI command, providing the target text and optional parameters like voice or style.
- The skill retrieves the MIMO_API_KEY from the Openclaw Skills configuration file or environment variables.
- The text is formatted with any selected style tags (e.g., Happy, Whisper) and sent to the Xiaomi MiMo V2 API endpoint.
- The API processes the request using a 24kHz sampling rate and generates a high-fidelity audio stream.
- The skill captures the response and saves the audio file to the local directory in the user-specified format (WAV or PCM16).
- A success response is returned in JSON format, providing metadata including file size and duration.
Xiaomi MiMo Voice TTS Setup
To use this feature within your Openclaw Skills environment, first install the required dependency:
pip install requests
Next, configure your API credentials in your ~/.openclaw/openclaw.json file:
{
"skills": {
"entries": {
"xiaomi-mimo-voice": {
"enabled": true,
"env": {
"MIMO_API_KEY": "your-api-key"
}
}
}
}
}
You can also export the key directly to your environment using export MIMO_API_KEY=your-api-key.
Xiaomi MiMo Voice TTS Data Schema & Taxonomy
The skill manages audio generation through a structured set of parameters and returns a comprehensive metadata object.
Input Parameters
| Parameter | Description | Default |
|---|---|---|
| --text | The content to be converted to speech | Required |
| --output | The destination path for the audio file | output.wav |
| --voice | The voice model (mimo_default, default_zh, default_en) | mimo_default |
| --style | Emotional or character-based style tags | None |
| --format | Output audio format (wav or pcm16) | wav |
Response Schema
Upon completion, the skill outputs a JSON object containing:
- status: The result of the operation.
- file: The path to the generated audio file.
- size_kb: The size of the output file.
- duration_sec: The length of the generated audio in seconds.
- voice/style/text: Metadata reflecting the original request configuration.
Xiaomi MiMo Voice TTS Advanced Features
- Multi-Emotional Support: Seamlessly switch between Happy, Sad, Angry, Fearful, and Disgusted emotional tones.
- Dialect Integration: Built-in support for multiple Chinese dialects to enhance localization in Openclaw Skills.
- Roleplay Presets: Specialized character voices for historical and fictional figures like Lin Daiyu and Guan Yu.
- Fine-grained Control: Adjust speaking speed (Speed up/Slow down) and vocal styles like Whisper or Clamped voice.
- High-Fidelity Sampling: Delivers professional-grade 24kHz PCM16 audio data for superior clarity.
SKILL.md
Loading
Related Openclaw Skills
Universal Deep Accessibility Analyzer
An enterprise-grade accessibility engine that combines real macOS VoiceOver simulation, AI-powered visual analysis, and deep crawling to ensure total WCAG 2.2 compliance.
Shopee Big Data Analytics
A comprehensive data intelligence agent for Shopee sellers to dominate Southeast Asian markets through advanced product selection and competitive analysis.
Baidu Netdisk Manager
A powerful cloud storage management skill for Baidu Netdisk that enables seamless file transfers and directory organization through AI-driven CLI commands.
Startup Helper
A comprehensive automation and advisory agent for navigating the administrative complexities of starting and operating a business in China.
Fragments
A sophisticated work-logging and idea-capture system that integrates Memos and daily journals directly into your AI agent's workflow.
Spark Memory
Spark Memory is an intelligence layer for AI agents that provides persistent long-term memory and autonomous overnight reflection to detect patterns and improve over time.
Featured*
