A high-performance voice suite providing emotion-aware text-to-speech and transcription for AI agents.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install mimo-voice-assistant
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 mimo-voice-assistant 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 MiMo Voice Assistant?
The MiMo Voice Assistant is a comprehensive end-to-end voice solution designed specifically for Openclaw Skills. By leveraging the Xiaomi MiMo-V2.5-TTS engine, it provides agents with the ability to generate speech that is not only high-quality but also emotion-aware and instruction-following. This skill allows developers to bridge the gap between text-based interactions and natural vocal communication.
Built to be multi-platform ready, it supports transcription via MiMo-V2-Omni and offers a proxy layer that mimics standard API formats for easy integration. Whether you are building for messaging apps or custom hardware, this tool provides the necessary vocal infrastructure for modern Openclaw Skills.
MiMo Voice Assistant Use Cases
- Powering realistic voice interactions in Telegram, Discord, or WhatsApp bots.
- Implementing personalized assistants using voice cloning from reference audio samples.
- Providing accessibility features through automated transcription of user voice messages.
- Deploying multilingual agents that automatically match the user's dialect and language in Openclaw Skills.
How MiMo Voice Assistant Works
- The Openclaw Skills agent receives an inbound audio message from a user platform.
- The audio is forwarded to the MiMo-V2-Omni transcription service to convert speech into text.
- The agent processes the text and determines the appropriate response and emotional tone.
- The response text is sent to the local MiMo TTS proxy along with style instructions or cloning data.
- The proxy communicates with the MiMo API to generate a high-fidelity audio file.
- The final voice reply is delivered back to the user through the original communication channel.
MiMo Voice Assistant Setup
To get started with this skill within the Openclaw Skills ecosystem, follow these steps:
# 1. Install necessary dependencies
cd mimo-tts-proxy && npm install
# 2. Set your MiMo API Key
export MIMO_API_KEY="your-key-here"
# 3. Launch the proxy server
node src/server.mjs
Configure your openclaw.json to utilize the local proxy at http://127.0.0.1:3999 as the TTS provider.
MiMo Voice Assistant Data Schema & Taxonomy
The skill organizes its data flow using a structured request format compatible with standard AI audio interfaces. Below is the metadata taxonomy for requests:
| Parameter | Type | Description |
|---|---|---|
| model | string | Specifies the version (e.g., tts-1). |
| input | string | The text content for synthesis. |
| voice | string | The target voice ID. |
| style | string | Natural language instructions for emotion or tone. |
| reference_audio | string | Base64 data used for real-time voice cloning. |
| response_format | string | Output type: mp3, wav, or opus. |
MiMo Voice Assistant Advanced Features
- Emotion-aware generation that responds to natural language style prompts like "speak with a gentle tone."
- Advanced voice cloning capabilities allowing for identity persistence across Openclaw Skills.
- Support for regional dialects including Cantonese, Taiwanese, and various mainland Chinese dialects.
- Automated language detection that ensures the TTS output always matches the user's input language without manual configuration.
- Token-based billing integration with off-peak discounts for cost-effective scaling of Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Facebook Ad Tracker & Monitor
A comprehensive tool for tracking Facebook advertisers, analyzing creative performance, and monitoring product trends via the PPSPY API.
Bilibili and Video Summarizer
A comprehensive video analysis tool that extracts subtitles, generates AI summaries, and scores information density for Bilibili, YouTube, Douyin, and local files.
Vheer AI Image to Video
Transform static images into dynamic, motion-filled cinematic video clips using advanced AI processing.
Hugo Blog Publisher
A powerful automation tool for publishing Markdown content to Hugo blogs with intelligent metadata generation and image management.
WeChat Media Downloader
A robust tool for extracting and downloading media from WeChat Official Account articles by leveraging verified browser sessions.
Cloudflare R2 S3 Storage Tool
A versatile utility for managing Cloudflare R2 storage using S3-compatible APIs to handle file uploads and public link generation.
Featured*
