Overview
- Skill Key
- axdlee/siliconflow-media
- Author
- axdlee
- Source Repo
- openclaw/skills
- Version
- -
- Source Path
- skills/axdlee/siliconflow-media
- Latest Commit SHA
- 1d802c1567a4eff68cf068441ffc7adcc09c876a
Official OpenClaw
rules
15%
siliconflow-media
SiliconFlow 多模态服务，支持图片生成(FLUX/Qwen)、视频生成(Wan)、TTS语音合成、ASR语音识别。使用代金券支付。
Stars
0
Installs
0
Status
ACTIVE
Visibility
PUBLIC
安装方式
直接复制以下提示词，发送给你的 AI 助手即可完成安装。
请先检查是否已安装 SkillHub 商店，若未安装，请根据 https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/skillhub.md 安装 SkillHub 商店，然后安装 siliconflow-media 技能。 若已安装，则直接安装 siliconflow-media 技能。
Extracted Content
SKILL.md excerpt
# SiliconFlow 媒体服务
SiliconFlow 提供丰富的 AI 模型服务，支持代金券支付（当前余额 3000+）。
## 环境变量
- `SILICONFLOW_API_KEY` - SiliconFlow API Key
## 🎨 图片生成
```bash
uv run {baseDir}/scripts/image_gen.py --prompt "描述" --filename "output.png" [--model MODEL]
```
**可用模型**：
| 参数 | 模型 | 说明 |
|------|------|------|
| `flux` (默认) | FLUX.1-schnell | 快速高质量，约 5-10 秒 |
| `flux-dev` | FLUX.1-dev | 开发版 |
| `flux-pro` | FLUX.1-pro | 专业版 |
| `qwen` | Qwen/Qwen-Image | 通义图片生成 |
| `qwen-edit` | Qwen/Qwen-Image-Edit | 图片编辑 |
| `qwen-edit-2509` | Qwen/Qwen-Image-Edit-2509 | 最新编辑版 |
**示例**：
```bash
# FLUX 快速生成
uv run {baseDir}/scripts/image_gen.py --prompt "a cute robot assistant" --filename "robot.png"
# Qwen 生成
uv run {baseDir}/scripts/image_gen.py --prompt "山水画" --filename "landscape.png" --model qwen
```
## 🎬 视频生成
```bash
# 文生视频
uv run {baseDir}/scripts/video_gen.py --prompt "描述" --filename "output.mp4"
# 图生视频
uv run {baseDir}/scripts/video_gen.py --prompt "描述" --image "input.png" --filename "output.mp4"
```
**模型**：
- 文生视频: `Wan-AI/Wan2.2-T2V-A14B`
- 图生视频: `Wan-AI/Wan2.2-I2V-A14B`
⚠️ 视频生成时间较长（约 2-5 分钟）
## 🎤 语音合成 (TTS)
```bash
uv run {baseDir}/scripts/tts.py --text "要合成的文字" --filename "output.mp3" [--model MODEL]
```
**可用模型**：
| 参数 | 模型 | 说明 |
|------|------|------|
| `fish-speech` (默认) | fish-speech-1.5 | Fish Audio 高质量 |
| `cosyvoice` | CosyVoice2-0.5B | 阿里语音克隆 |
| `indextts` | IndexTTS-2 | Index TTS |
| `moss` | MOSS-TTSD-v0.5 | MOSS 多语言 |
**示例**：
```bash
uv run {baseDir}/scripts/tts.py --text "你好世界" --filename "hello.mp3"
```
## 👂 语音识别 (ASR)
```bash
uv run {baseDir}/scripts/asr.py --audio "input.mp3" [--model MODEL]
```
**可用模型**：
| 参数 | 模型 | 说明 |
|------|------|------|
| `sensevoice` (默认) | SenseVoiceSmall | 阿里语音识别 |
| `teleai` | TeleSpeechASR | TeleAI 识别 |
**示例**：
```bash
uv run {b...
Related Claw Skills
capt-marbles
Task Router Skill
Task Router
captchasco
captchas-openclaw
OpenClaw integration guidance for CAPTCHAS Agent API, including OpenResponses tool schemas and plugin tool registration.
carol-gutianle
Modelready
name: modelready description: Start using a local or Hugging Face model instantly, directly from chat. metadata: {"openclaw":{"requires":{"bins": "bash", "curl" }, "env": "URL" }}
cartoonitunes
Ethereum History
Read-only factual data about historical Ethereum mainnet contracts. Use when the user asks about a specific contract address, early Ethereum contracts, deployment era, deployer, bytecode, decompiled code, or documented history (what a contract is and is not). Data is non-opinionated and includes runtime bytecode, decompiled code, and editorial history when available. Base URL https://ethereumhistory.com (or set BASE_URL for local/staging).
cassh100k
agent-dna
Portable agent identity encoding. Compress SOUL.md/MEMORY.md into transferable DNA fingerprints, detect identity drift between snapshots, and port personality across platforms (OpenClaw, Claude, GPT, CrewAI). Pure Python, zero dependencies. Use when migrating agents between platforms, detecting personality drift, or backing up agent identity.
camopel
storage-cleanup
One-command disk cleanup for macOS and Linux — trash, caches, temp files, old kernels, snap revisions, Homebrew, Docker, and Xcode artifacts. Use when user asks to free storage, clean up disk, reclaim space, reduce disk usage, or encounters low disk / "disk full" warnings. Safe by default with dry-run mode. No dependencies beyond bash and awk.