MiMo-Skills
Text-to-speech synthesis, voice cloning, and voice design
All Skills in This Repository (1)
Pure Emerald Level IndicatorsFrequently Asked Questions
FAQPage SchemaHow to install MiMo-Skills?▼
Run `npx skills add XiaomiMiMo/MiMo-Skills --all -g -y` in your terminal to install the skill globally. You will also need a MiMo API key set as the MIMO_API_KEY environment variable.
How to convert text to speech with MiMo?▼
Ask your agent to read text aloud and it runs the mimo_tts.py script with your chosen preset voice. You can control emotion, speed, and style using plain-language instructions or inline tags.
Can MiMo clone a voice from an audio sample?▼
Yes. Provide an mp3 or wav sample under 10 MB and the voice cloning script reproduces that voice for any new text you supply.
Does MiMo TTS support singing and dialects?▼
Yes. Preset voices support singing via a simple tag, and you can apply dialects like Cantonese or Sichuanese plus dozens of emotion and tone styles.
Can I send generated voice messages to Feishu?▼
Yes. The included script converts the audio to opus, uploads it, and sends it as a native voice message to Feishu private or group chats.
Related Repositories in Content & Communication
View All in Content & Communication→
anthropicsskills
Official Anthropic skills for documents, design, and developer workflows
bladerhumanizer
Rewrite AI-sounding text so it reads like a person wrote it
DevolutionsUniGetUI
Automate software translation reviews, diffs, and localization quality checks