← Back to Skills Marketplace
344
Downloads
0
Stars
1
Active Installs
6
Versions
Install in OpenClaw
/install moss-voice-generator
Description
MOSI Studio 指令式音色生成（moss-voice-generator）： 用自然语言描述想要的音色风格，无需指定预设 voice_id， 模型根据描述实时生成对应的声音。 触发词：指令式语音、按描述生成声音、自定义音色、描述一个声音、 "voice generator"、"generate voice...
Usage Guidance
This skill will send the text and your style description to studio.mosi.cn using the MOSI_TTS_API_KEY and save the returned WAV in your OpenClaw workspace. Only provide an API key you trust with that service. Ensure curl, jq, and base64 are available. Be mindful of privacy and legal/ethical rules when generating voices (do not impersonate real people without consent). If you do not trust studio.mosi.cn or the API key provenance, do not install or provide credentials.
Capability Analysis
Type: OpenClaw Skill
Name: moss-voice-generator
Version: 1.0.5
The moss-voice-generator skill is a legitimate tool for generating synthetic speech via the MOSI Studio API. The core script, mosi_voice_generator.sh, uses jq for secure JSON construction and curl to communicate with the official endpoint (studio.mosi.cn). No evidence of data exfiltration, malicious execution, or prompt injection was found; the skill operates as described in its documentation.
Capability Assessment
Purpose & Capability
Name/description promise an instruction-driven TTS. The skill only requires MOSI_TTS_API_KEY and standard CLI tools (curl, jq, base64) which are appropriate and proportional to calling the MOSI Studio TTS API.
Instruction Scope
SKILL.md and the included script limit actions to building a JSON payload, POSTing to https://studio.mosi.cn/api/v1/audio/speech, decoding returned base64 audio_data to a WAV file, and referencing a workspace output path. No unrelated file reads, extra env vars, or other external endpoints are present.
Install Mechanism
No install spec or external downloads; this is instruction-only with a small included shell script. Nothing is written beyond the user's workspace output file and standard CLI usage.
Credentials
Only MOSI_TTS_API_KEY is declared and used (also exposed as --api-key option). No other secrets or unrelated credentials are requested or referenced.
Persistence & Privilege
Skill is not forced-always, does not request elevated/system-wide privileges, and does not modify other skills or system configs. Autonomous invocation is allowed (platform default) but not combined with other red flags.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install moss-voice-generator - After installation, invoke the skill by name or use
/moss-voice-generator - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.5
Fix: use metadata.openclaw.requires.env and primaryEnv to declare MOSI_TTS_API_KEY
v1.0.4
Trigger rescan: env and homepage declared, no node/eval patterns
v1.0.3
Fix: remove undocumented --meta-info flag from docs (not implemented in script)
v1.0.2
Fix: declare MOSI_TTS_API_KEY env, add homepage, remove node dep (uses curl+jq+base64)
v1.0.1
Fix: replace node -e inline JS with jq+base64 to avoid eval flag
v1.0.0
Initial release: 用自然语言描述生成音色，无需预设 voice_id
Metadata
Frequently Asked Questions
What is MOSS Voice Generator 指令式音色生成?
MOSI Studio 指令式音色生成（moss-voice-generator）： 用自然语言描述想要的音色风格，无需指定预设 voice_id， 模型根据描述实时生成对应的声音。 触发词：指令式语音、按描述生成声音、自定义音色、描述一个声音、 "voice generator"、"generate voice... It is an AI Agent Skill for Claude Code / OpenClaw, with 344 downloads so far.
How do I install MOSS Voice Generator 指令式音色生成?
Run "/install moss-voice-generator" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is MOSS Voice Generator 指令式音色生成 free?
Yes, MOSS Voice Generator 指令式音色生成 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does MOSS Voice Generator 指令式音色生成 support?
MOSS Voice Generator 指令式音色生成 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created MOSS Voice Generator 指令式音色生成?
It is built and maintained by YYL (@mkkb473); the current version is v1.0.5.
More Skills