MOSS-TTS Voice
v1.2.2MOSS-TTS 语音合成与音色克隆工具。生成适合各渠道的音频文件。 触发场景： - 用户要求生成语音、TTS - 用户提到"用我的声音"、"克隆声音"、"MOSS语音" - 需要生成语音文件用于发送 功能：文本转语音、实时克隆、预注册音色、多格式输出
⭐ 7· 948·8 current·8 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (TTS and voice cloning) match the files, CLI scripts, and the single required credential (MOSS_API_KEY). Required binaries (python3, ffmpeg) are appropriate for audio conversion and running the Python scripts.
Instruction Scope
SKILL.md and scripts instruct uploading reference audio and sending TTS requests to studio.mosi.cn, and they write temporary files under /tmp. This is expected for a cloning/TTS tool, but it does involve transmitting user audio to a third-party service — the README and SKILL.md do warn about this. Users should be aware that uploaded audio is stored on the remote service.
Install Mechanism
No install spec; the skill is instruction-plus-scripts only and relies on standard system packages and pip-installed requests. No remote arbitrary downloads or archive extraction are performed by the skill itself.
Credentials
Only one environment variable (MOSS_API_KEY) is required and is the expected credential for calls to the documented MOSS Studio endpoints. The scripts read no other secrets or unrelated system configuration paths.
Persistence & Privilege
Skill does not request always:true, does not modify other skills or system settings, and has no elevated persistence requirements. It writes temporary output to /tmp and a skill-specific folder under /tmp, which is reasonable for a CLI tool.
Assessment
This skill appears to do what it says: generate TTS and clone voices via the MOSS Studio API. Before installing: 1) Only provide a MOSS_API_KEY you trust and consider using a dedicated key with limited scope if the provider supports it; 2) Do not upload sensitive or private recordings — the tool uploads reference audio to the remote service and the vendor stores cloned voices; 3) Verify ffmpeg and python are installed from trusted sources; 4) Review the vendor's privacy policy on studio.mosi.cn for retention and sharing rules; 5) If you need to send generated files into messaging platforms, use separate delivery tools as the skill only produces files. If you want a deeper audit, request network logs or confirm exact API endpoints/paths with the vendor (there are minor endpoint name variants in docs vs. code).Like a lobster shell, security has layers — review code before you run it.
latestvk9704tz8nb5refkh7bbmp7gs7h82td2x
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🎙️ Clawdis
Binspython3, ffmpeg
EnvMOSS_API_KEY
Primary envMOSS_API_KEY