MiMo TTS 2.5 Plus for Openclaw

An advanced text-to-speech integration featuring high-fidelity voice cloning, emotional character direction, and custom voice design capabilities.

limingjing6666
v1.3.1
May 2, 2026
0
845
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install mimotts25-plus

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install mimotts25-plus 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 TTS 2.5 Plus?

The MiMo TTS 2.5 Plus skill is a powerful audio generation tool built for Openclaw Skills that transforms static text into expressive, human-like speech. Unlike traditional text-to-speech engines, this enhanced version utilizes a dual-parameter approach where the spoken text is separated from the emotional context. By providing specific instructions regarding speed, tone, and atmosphere, developers can create highly nuanced vocal performances that range from energetic youth to steady, mature narrators.

MiMo TTS 2.5 Plus Use Cases

  • Creating immersive roleplay experiences where AI characters exhibit genuine emotional fluctuations.
  • Developing branded virtual assistants with unique, custom-designed voice identities.
  • Automating high-quality voiceover production for social media and presentations using Openclaw Skills.
  • Implementing real-time vocal feedback in smart home or productivity environments with specific atmospheric tones.

How MiMo TTS 2.5 Plus Works

  1. The AI agent analyzes the intent and emotion of the response to be spoken.
  2. Contextual metadata including mood, speed, and character traits are packaged into the context parameter.
  3. Speech enhancement tags such as pauses or sighs are naturally injected into the target text.
  4. The skill selects the appropriate MiMo script based on whether the task requires a preset voice, a cloned voice, or a descriptive design.
  5. The MiMo API processes the request and generates a high-quality MP3 file for immediate playback or storage.

MiMo TTS 2.5 Plus Setup

To get started with MiMo TTS 2.5 Plus in your Openclaw Skills workflow, follow these steps:

  1. Obtain an API Key from the Xiaomi MiMo Open Platform.
  2. Set the environment variable in your terminal:
export MIMO_API_KEY="your_key_here"
  1. Alternatively, use the Openclaw configuration command:
openclaw config set skills.entries.mimotts25-plus.apiKey "your_key_here"

MiMo TTS 2.5 Plus Data Schema & Taxonomy

The skill organizes input and output through a structured command-line interface and specific metadata triggers.

Component Type Description
--text String The actual words to be spoken, including style and inline tags.
--context String Mandatory emotional and environmental instructions for the AI.
--voice String The ID of the preset voice (e.g., Bing Tang, Molly, Dean).
--voice-file File Path to an MP3 sample for voice cloning.
Output Path Returns a string in the format MEDIA:output.mp3.

MiMo TTS 2.5 Plus Advanced Features

  • Director Mode: Allows for complex layering of role identity, scene description, and technical guidance for cinematic vocal results.
  • Voice Design: Generates completely new vocal profiles based on four-dimensional descriptions (Age/Gender, Texture, Emotion, Rhythm).
  • Inline Audio Tags: Support for specific acoustic events like [deep breath], [laughter], or [whispering] within the speech flow.
  • Flexible API Clusters: Ability to toggle between global and region-specific API endpoints to optimize latency for Openclaw Skills users.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*