← Back to Skills Marketplace
373
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install moss-tts-family-chatbot
Description
MOSI Studio 音频全套能力：语音转文字（ASR）、文字转语音（TTS）、 多说话人对话合成、声音克隆、飞书语音气泡。 两类触发场景： 1. 消息中包含 "[media attached:"、"audio/ogg"、"audio/opus" 或 路径 /home/openclaw/.openclaw/me...
Usage Guidance
This skill appears to implement the advertised MOSI Studio audio features, but the package metadata fails to declare required credentials and contains inconsistent env var names. Before installing: 1) confirm which environment variables the runtime expects (MOSI_TTS_API_KEY vs MOSI_API_KEY) and ensure they are set correctly and scoped/rotated; 2) if you want Feishu voice bubbles, be aware the script requires FEISHU_APP_ID and FEISHU_APP_SECRET (not declared) and will call open.feishu.cn to obtain a tenant token and upload/send files; only provide least-privilege credentials and test in a restricted environment; 3) note the skill will auto-transcribe inbound media paths (it instructs immediate transcription) — ensure you are comfortable with automatic processing of inbound audio; 4) run the scripts in a sandbox first to verify network endpoints, rate limits, and where files are written; and 5) ask the skill author to update the registry metadata to explicitly list required env vars, any binary prerequisites, and the exact scope of tokens used so you can perform a proper risk review.
Capability Analysis
Type: OpenClaw Skill
Name: moss-tts-family-chatbot
Version: 0.0.4
The skill bundle provides a comprehensive suite of audio processing tools (TTS, ASR, voice cloning) and Feishu integration via the MOSI Studio API (studio.mosi.cn). The scripts (e.g., mosi_tts.sh, mosi_asr.sh, mosi_feishu_voice.sh) use standard tools like curl, ffmpeg, and node to interact with legitimate endpoints and handle media files within the designated workspace directory (~/.openclaw/workspace/). There is no evidence of data exfiltration, malicious execution, or harmful prompt injection; the instructions in SKILL.md are focused on ensuring the agent correctly utilizes the provided scripts and respects security boundaries regarding API keys.
Capability Assessment
Purpose & Capability
The name/description (TTS, ASR, multi-speaker, voice clone, Feishu voice bubbles) align with the included scripts and API docs (calls to https://studio.mosi.cn). However the registry metadata declares no required env vars or binaries while the scripts require API keys and Feishu credentials; also the code uses two different MOSI API env names (MOSI_TTS_API_KEY vs MOSI_API_KEY). The presence of Feishu upload/send logic is consistent with the 'Feishu voice bubble' feature, but those credentials are not declared in the skill metadata.
Instruction Scope
SKILL.md instructs the agent to immediately transcribe inbound media (matching a specific injected message pattern) and to save all generated audio under ~/.openclaw/workspace. The instructions reference reading inbound media paths (/home/openclaw/.openclaw/media/inbound/...), calling external APIs, and using Feishu tenant credentials to upload/send audio. These actions are within the stated audio/Feishu integration scope but the 'must immediately transcribe' requirement gives the skill autonomous behavior that could process any incoming media without extra confirmation.
Install Mechanism
No install spec; this is instruction-and-script-only. That lowers install risk because nothing is downloaded at install time. The scripts assume common CLI tools (node, curl, ffmpeg, python3, etc.) but do not perform external downloads.
Credentials
The registry metadata lists no required environment variables, but the SKILL.md and scripts require at least MOSI_TTS_API_KEY / MOSI_API_KEY and, for Feishu integration, FEISHU_APP_ID and FEISHU_APP_SECRET (used by scripts/mosi_feishu_voice.sh). This is an inadequate declaration of secrets. Also inconsistent env var naming (MOSI_TTS_API_KEY vs MOSI_API_KEY) could cause misconfiguration or accidental exposure. The number and type of required secrets is reasonable for the features, but they must be declared and scoped—right now they are not.
Persistence & Privilege
always is false and the skill does not request forced inclusion. The skill writes only to its workspace (~/.openclaw/workspace) as required by media policy, and does not attempt to modify other skills or system-wide configs in the provided files.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install moss-tts-family-chatbot - After installation, invoke the skill by name or use
/moss-tts-family-chatbot - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.0.4
**Summary:**
Expanded description: added multi-feature audio capability details, strict file path rules, supported operations, dependencies, and usage examples for multiple audio tasks.
- Added detailed descriptions of supported audio features: ASR, TTS, multi-speaker dialogue synthesis, voice cloning, and Feishu voice bubbles.
- Clarified strict file path requirements for generated audio outputs.
- Listed and explained all script entry points and available audio models.
- Provided comprehensive usage instructions for each capability (including sample scripts and parameter explanations).
- Documented environment preparation steps, dependency handling, troubleshooting, and installation methods.
- Included best practices, feature usage guides, and common pitfalls for users.
Metadata
Frequently Asked Questions
What is moss-tts-family-chatbot?
MOSI Studio 音频全套能力：语音转文字（ASR）、文字转语音（TTS）、 多说话人对话合成、声音克隆、飞书语音气泡。 两类触发场景： 1. 消息中包含 "[media attached:"、"audio/ogg"、"audio/opus" 或 路径 /home/openclaw/.openclaw/me... It is an AI Agent Skill for Claude Code / OpenClaw, with 373 downloads so far.
How do I install moss-tts-family-chatbot?
Run "/install moss-tts-family-chatbot" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is moss-tts-family-chatbot free?
Yes, moss-tts-family-chatbot is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does moss-tts-family-chatbot support?
moss-tts-family-chatbot is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created moss-tts-family-chatbot?
It is built and maintained by YYL (@mkkb473); the current version is v0.0.4.
More Skills