Menu
MOSS-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
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | moss-tts-voice |
| description | MOSS-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 |
| metadata | {"openclaw":{"requires":{"env":["MOSS_API_KEY"],"bins":["python3","ffmpeg"]},"primaryEnv":"MOSS_API_KEY","homepage":"https://studio.mosi.cn","emoji":"🎙️"}} |
⚠️ 注意：本工具负责生成音频文件，发送到各渠道需要配合其他工具（如 OpenClaw message 工具）
访问 https://studio.mosi.cn → 注册/登录 → 控制台 → API 密钥 → 创建
export MOSS_API_KEY="sk-你的密钥"
# 系统依赖
brew install python3 ffmpeg
# Python 依赖
pip3 install requests
python3 scripts/tts.py \
--text "你好，我是MOSS" \
--channel feishu \
--json
输出：
{
"success": true,
"file": "/tmp/openclaw/moss-tts/voice-xxx.ogg",
"format": "ogg"
}
MOSS_API_KEY 添加到 .gitignore建议：
本工具提供以下功能：
不包含：
python3 scripts/tts.py \
--text "要说的内容" \
--reference_audio "参考音频.ogg" \
--channel feishu
# 1. 上传并克隆
curl -X POST https://studio.mosi.cn/api/v1/files/upload \
-H "Authorization: Bearer $MOSS_API_KEY" \
-F "file=@voice.ogg"
# → {"file_id": "YOUR_FILE_ID"}
curl -X POST https://studio.mosi.cn/api/v1/voice/clone \
-H "Authorization: Bearer $MOSS_API_KEY" \
-d '{"file_id": "YOUR_FILE_ID", "name": "我的声音"}'
# → {"voice_id": "YOUR_VOICE_ID"}
# 2. 使用（等待 10 秒后）
python3 scripts/tts.py \
--text "你好" \
--voice_id "YOUR_VOICE_ID" \
--channel feishu
| 渠道 | 格式 | 说明 |
|---|---|---|
| feishu | ogg (opus) | 飞书语音消息格式 |
| telegram | ogg (opus) | Telegram 语音消息格式 |
| ogg (opus) | WhatsApp 语音消息格式 | |
| discord | mp3 | Discord 文件格式 |
| signal | mp3 | Signal 文件格式 |
| slack | mp3 | Slack 文件格式 |
| 参数 | 说明 | 必填 |
|---|---|---|
--text | 待合成文本 | ✅ |
--reference_audio | 参考音频（实时克隆） | 二选一 |
--voice_id | 预注册音色 ID | 二选一 |
--channel | 目标渠道 | ❌ |
--format | 输出格式 | ❌ |
--output | 输出路径 | ❌ |
--json | JSON 输出 | ❌ |
本工具只生成音频文件。发送需要：
确保音频格式正确：
file voice.ogg
# 应显示: Ogg data, Opus audio
| 用途 | 端点 |
|---|---|
| 文本转语音 | POST /v1/audio/tts |
| 上传文件 | POST /api/v1/files/upload |
| 克隆音色 | POST /api/v1/voice/clone |
| 查询音色 | GET /api/v1/voices |
版本: 1.2.0 | 更新: 2026-03-10
Connect to 100+ APIs (Google Workspace, Microsoft 365, GitHub, Notion, Slack, Airtable, HubSpot, etc.) with managed OAuth. Use this skill when users want to interact with external services. Security: The MATON_API_KEY authenticates with Maton.ai but grants NO access to third-party services by itself. Each service requires explicit OAuth authorization by the user through Maton's connect flow. Access is strictly scoped to connections the user has authorized. Provided by Maton (https://maton.ai).
Search and summarize papers from ArXiv. Use when the user asks for the latest research, specific topics on ArXiv, or a daily summary of AI papers.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Use when the user mentions free AI, OpenRouter, model switching, rate limits, or wants to reduce AI costs.
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Use when the user mentions free AI, OpenRouter, model switching, rate limits, or wants to reduce AI costs.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.