← Back to Skills Marketplace
113
Downloads
1
Stars
0
Active Installs
13
Versions
Install in OpenClaw
/install mimo-tts-asr-26-free
Description
Mimo TTS ASR 2.6 Free for Now! Xiaomi MiMo V2.5 TTS + ASR all-in-one voice skill. Supports high-quality Chinese/English TTS and ASR. TTS: 3 models (Premium V...
Usage Guidance
This skill appears to implement the advertised TTS/ASR features, but there are a few things to check before installing:
- Metadata mismatch: the registry lists no required env vars, but SKILL.md and the scripts require MIMO_API_KEY and/or MIMO_ASR_KEY (ASR will abort if no key). Confirm whether you must provide API keys.
- External network use: audio and reference samples will be uploaded to api.xiaomimimo.com (or a custom MIMO_API_ENDPOINT). If you have privacy concerns, do not upload sensitive audio or reference voice samples.
- ASR vs. fallback: TTS can fallback to local edge-tts when no key is present, but ASR appears to require a key — the docs are ambiguous about this. Expect ASR to be cloud-only unless you run your own ASR models locally.
- Dependencies and system calls: the scripts invoke ffmpeg and use subprocess; install ffmpeg in a controlled environment and audit subprocess calls if you will run on sensitive systems.
- Source trust: the skill's source and owner are unknown and there's no homepage. If you don't trust the author, run it in a sandboxed environment or review the full scripts (they are included) before use.
Recommended actions: verify the author/source, confirm whether you need to supply API keys, review the scripts (they are included) for any unexpected network calls, and run the skill in an isolated container or VM if you will process private audio or use voice cloning.
Capability Tags
Capability Assessment
Purpose & Capability
The SKILL.md and included scripts clearly implement TTS and ASR and call a remote API (api.xiaomimimo.com) and/or local edge-tts. However the registry metadata listed no required environment variables or credentials, while the documentation and code require MIMO_API_KEY and/or MIMO_ASR_KEY (ASR script will exit if no key). This mismatch between declared requirements and actual needs is incoherent and surprising.
Instruction Scope
The runtime instructions and scripts stay within TTS/ASR functionality (preprocess audio, call remote API, fallback to edge-tts, caching, chunking). They do perform file I/O (read/write audio, create cache dir), spawn ffmpeg via subprocess, and upload audio to a remote API endpoint — all expected for this purpose. Minor inconsistency: SKILL.md states 'no Key also can use' (edge-tts fallback) but ASR script enforces a key; the doc's wording around ASR availability is ambiguous.
Install Mechanism
There is no install spec that downloads arbitrary archives; the package is instruction-only with included Python scripts. Dependencies are installed via pip per the README (openai, edge-tts). No remote download URLs or extraction steps are present in the install metadata.
Credentials
Using an API key (MIMO_API_KEY / MIMO_ASR_KEY) is proportionate to contacting a cloud TTS/ASR service. The concern is that the registry metadata omitted required env vars while SKILL.md and the scripts require them. Also the skill exposes an API endpoint base_url that points to https://api.xiaomimimo.com/v1 — you should expect audio and possibly voice-clone data (reference audio) to be uploaded to that external service; this is expected for cloud TTS but relevant for privacy.
Persistence & Privilege
The skill does not request always: true and does not modify other skills' configs. It creates a local cache directory inside the skill workspace and uses /tmp for temporary files — normal for this kind of tool.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install mimo-tts-asr-26-free - After installation, invoke the skill by name or use
/mimo-tts-asr-26-free - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.99.92
批量合成、智能音色推荐、格式自动检测、默认预处理、质量自检、目录监听、性能基准、费用说明、质量对比表
v2.99.3
新增导演剧本级结构化输入、文本理解能力说明、MiMo Studio 链接、作者对比分析表
v2.99.2
新增声音克隆文档、唱歌模式、文本规范化指南、环境变量覆盖表、输出格式保证、故障排查扩展
v2.99.0
v2.99.0 introduces improved stability, control, and privacy for TTS synthesis:
- 防限流：新增随机延迟与最大并发限制，减轻接口限流压力
- 长文本自动分句分段（120字/段，按标点切分）提升合成成功率
- 502/503/超时自动重试，异常捕获更健壮
- 隐私增强：API Key 不再输出日志、临时文件自动清理
- 新增 USE_CLOUD_TTS 一键切换本地/edge-tts
- 细节改进：风格描述补充、缓存缓存持久化、ffmpeg 缺失提示优化
v2.98.0
**v2.98.0 Changelog**
- 增加 edge-tts 免费 fallback：未配置 MIMO_API_KEY 时自动切换到 edge-tts 通道
- 预置音色表补充风格描述（如“活泼少女”“知性女声”），并文档说明可自动匹配 edge-tts 音色
- 缓存目录调整为 `{baseDir}/cache`，支持持久化缓存
- 缺失 ffmpeg 时输出明确提示
- 默认给 scripts 增加执行权限
- 文档同步更新，突出免费 fallback，对标 推荐场景与开源备选方案
v2.97.0
MiMo TTS & ASR v2.97 highlights:
- 新增「开源免费 TTS 备选方案」推荐，包括 edge-tts、ChatTTS、CosyVoice、fish-speech 等项目简介和安装指引。
- 增加「GitHub TTS 项目星数 Top 5」板块，便于对比主流项目和技术选择。
- 给出推荐 TTS 组合搭配建议：MiMo TTS 云端免费主用，edge-tts 备用，GPT-SoVITS 支持自建语音克隆。
v2.95.0
MiMo TTS & ASR v2.95 — Free For Now
- 重新命名并突出“限时免费”与 TTS/ASR 联合能力
- 默认音色调整为“冰糖”，示例音色修订为实际可用
- `--speed` 和 `--pitch` 标注为“预留参数”（暂不生效）
- ASR 云端功能当前未开放，文档中予以标注说明
- 若干参数与环境变量说明简化，聚焦核心用法
v2.92.0
- 新增 scripts/tts.py：三合一 TTS 脚本，支持预置音色、音色设计、音色克隆
- 新增 scripts/asr.py：离线 ASR 语音识别脚本
- 新增 _meta.json 文件
- SKILL.md 标题更新为 MiMo TTS，并添加 v2.92 版本历史
- API 对接至 https://api.xiaomimimo.com/v1
v2.9.0
SKILL.md 精简重构(600→190行)，进阶内容拆至 docs/advanced.md，参数表统一，示例精简到核心场景，修复 --preprocess 语义矛盾
v2.8.1
Version 2.8.1
- Added explicit instructions requiring installation of ffmpeg/ffprobe and python3 as mandatory system dependencies.
- Clarified that ffmpeg/ffprobe are essential for audio preprocessing, chunking, and format conversion, and noted errors if missing.
- Revised API Key documentation for clarity; the environment variables MIMO_API_KEY and MIMO_ASR_KEY are now described as required.
- Documented that ASR open-source/local deployment does not require an API Key.
- Minor updates to version number and formatting for consistency.
v2.8.0
Mimo TTS ASR 2.8.0 is a version bump with changelog updates.
- Updated SKILL.md to reflect version 2.8.
- No feature or functional changes; documentation and version number updated.
v2.7.0
Mimo TTS ASR 2.7.0 introduces new advanced options for TTS and ASR scripts.
- Added TTS options: inference optimization (--optimize), text preprocessing, speech speed/pitch control, denoise, normalization, audio cache.
- Added ASR options: audio preprocessing, force disable diarization, Chinese decoder boost, audio chunking for long audio.
- Updated documentation and usage examples to reflect new parameters.
- General improvements to script flexibility and user control.
v2.6.0
- MiMo TTS ASR 2.6 released — all TTS and ASR features are now free for a limited time.
- Adds three TTS models: Premium Voices, VoiceDesign (description-based new voice creation), and VoiceClone (audio-based voice cloning), including emotion and style controls, multiple voice types, dialects, and export formats.
- ASR upgrades: high-accuracy speech-to-text, supports Chinese/English, dialects, code-switching, strong noise robustness, multi-speaker recognition, and flexible output options.
- ASR engine and models are open-sourced for local deployment; provides demo, code, and HuggingFace resources.
- Full official documentation, quick-start examples, usage guides, and troubleshooting included.
Metadata
Frequently Asked Questions
What is Mimo Tts Asr 26 Free?
Mimo TTS ASR 2.6 Free for Now! Xiaomi MiMo V2.5 TTS + ASR all-in-one voice skill. Supports high-quality Chinese/English TTS and ASR. TTS: 3 models (Premium V... It is an AI Agent Skill for Claude Code / OpenClaw, with 113 downloads so far.
How do I install Mimo Tts Asr 26 Free?
Run "/install mimo-tts-asr-26-free" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Mimo Tts Asr 26 Free free?
Yes, Mimo Tts Asr 26 Free is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Mimo Tts Asr 26 Free support?
Mimo Tts Asr 26 Free is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Mimo Tts Asr 26 Free?
It is built and maintained by aaroncxxx (@aaroncxxx); the current version is v2.99.92.
More Skills