首页 › 龙虾技能列表 › SiliconFlow TTS Gen — 技能工具

SiliconFlow TTS Gen — 技能工具

v1.0.0

[自动翻译] Text-to-Speech using SiliconFlow API (CosyVoice2). Supports multiple voices, languages, and dialects.

0· 711·4 当前·4 累计
by @lilei0311 (MaxStormSpace)·MIT-0
下载技能包
License
MIT-0
最后更新
2026/4/11
安全扫描
VirusTotal
可疑
查看报告
OpenClaw
安全
high confidence
The skill's code, instructions, and requested credential (SILICONFLOW_API_KEY) align with its stated TTS purpose; no obvious exfiltration or unrelated capabilities were found.
评估建议
This skill appears to do what it says: convert text to speech via the SiliconFlow API. Before installing, (1) verify the SiliconFlow domain (api.siliconflow.cn) and that you trust the service and its API key handling; (2) inspect ~/.openclaw/openclaw.json for other stored credentials before allowing the skill to read it, or set SILICONFLOW_API_KEY in the environment instead; (3) consider providing a scoped API key (least privilege) and monitor network use if you are concerned. Note the small man...
详细分析 ▾
✓ 用途与能力
Name/description, skill.json, SKILL.md and the script all target SiliconFlow TTS and only require an API key and produce audio files. The network host used (api.siliconflow.cn) is consistent with the stated service.
ℹ 指令范围
Runtime instructions and the script are narrowly scoped to: obtain an API key (from environment or ~/.openclaw/openclaw.json), call the SiliconFlow TTS endpoint, save an audio file, and print JSON results. The only broader action is reading ~/.openclaw/openclaw.json to auto-detect keys; this is explained in SKILL.md but could expose any keys stored there if the file is shared—script only accesses a specific providers.siliconflow.apiKey path.
✓ 安装机制
No install spec that downloads external code; this is an instruction + shipped Python script. No remote installs, archive downloads, or non-standard binary placement were observed.
ℹ 凭证需求
The only required secret is SILICONFLOW_API_KEY (declared in SKILL.md and skill.json), which is appropriate for an API-backed TTS skill. There is a minor metadata inconsistency: the top registry summary listed 'Required env vars: none' while SKILL.md and skill.json require SILICONFLOW_API_KEY—this is a documentation/manifest mismatch to be aware of.
✓ 持久化与权限
Skill does not request always:true, does not modify other skills or system settings, and only uses exec to run curl via subprocess (normal for a small CLI tool).
安全有层次，运行前请审查代码。

License

MIT-0

可自由使用、修改和再分发，无需署名。

运行时依赖

无特殊依赖

版本

latestv1.0.02026/2/15

- Initial release of siliconflow-tts-gen skill. - Provides Text-to-Speech generation via SiliconFlow API (CosyVoice2). - Supports 8 preset voices (4 male, 4 female) and multiple languages including Chinese, English, Japanese, and Korean. - Includes rapid voice cloning (3 seconds), Chinese dialects, and ultra low latency (150ms first packet delay). - Auto-downloads audio, configurable output formats, and supports local config and environment variable for API keys.

● 可疑

安装命令 点击复制

官方npx clawhub@latest install siliconflow-tts-gen
镜像加速npx clawhub@latest install siliconflow-tts-gen --registry https://cn.clawhub-mirror.com

技能文档

Text-to-Speech using SiliconFlow API with CosyVoice2 model. Supports 8 preset voices, multiple languages, and Chinese dialects.

Features

  • 🎙️ 8 Preset Voices: 4 male + 4 female voices
  • 🌍 Multilingual: Chinese, English, Japanese, Korean
  • 🗣️ Chinese Dialects: Cantonese, Sichuan, Shanghai, Tianjin, Wuhan
  • ⚡ Ultra Low Latency: 150ms first packet delay
  • 🎵 Voice Cloning: 3-second rapid voice cloning
  • 💾 Auto Download: Saves audio files locally

Requirements

  • Environment Variable: SILICONFLOW_API_KEY
  • Optional Config File: ~/.openclaw/openclaw.json (for auto-detect)

Installation

npx clawhub install siliconflow-tts-gen

Configuration

Set your SiliconFlow API key:

export SILICONFLOW_API_KEY="your-api-key"

Usage

List Available Voices

python3 scripts/generate.py --list-voices

Generate Speech

# Basic usage (default voice: alex)
python3 scripts/generate.py "你好，世界"
# Specify voice
python3 scripts/generate.py "Hello World" --voice bella
# Adjust speed
python3 scripts/generate.py "你好" --voice claire --speed 0.9
# Save to file
python3 scripts/generate.py "欢迎收听" --output welcome.mp3
# Change format
python3 scripts/generate.py "Hello" --format wav

Available Voices

Male Voices

IDNameCharacteristic
alex沉稳男声Mature and steady
benjamin低沉男声Deep and low
charles磁性男声Magnetic
david欢快男声Cheerful

Female Voices

IDNameCharacteristic
anna沉稳女声Mature and elegant
bella激情女声Passionate
claire温柔女声Gentle and kind
diana欢快女声Sweet and happy

Parameters

ParameterTypeDefaultRangeDescription
--voicestringalex-Voice ID
--speedfloat1.00.25-4.0Speech speed
--formatstringmp3mp3/opus/wav/pcmOutput format
--outputstringoutput.mp3-Output file path

Security Notes

  • This skill requires an API key to call SiliconFlow services
  • The script reads ~/.openclaw/openclaw.json only to auto-detect API keys
  • No sensitive data is transmitted except to api.siliconflow.cn
  • Review the code at scripts/generate.py before providing credentials

Author

MaxStorm Team

License

MIT

数据来源：ClawHub ↗ · 中文优化：龙虾技能库
OpenClaw 技能定制 / 插件定制 / 私有工作流定制

免费技能或插件可能存在安全风险，如需更匹配、更安全的方案，建议联系付费定制

了解定制服务