OpenClaw AI 技能

创建s coaching and scaling videos for CrossFit workouts to showcase gym community, athlete 进度, and inclusive programming to attract and retAIn members.

创建s short preview and marketing videos showcasing scuba diving experiences, instructors, and customer reactions to boost bookings for scuba schools.

创建s program overview and 命令行工具ent journey videos to help wellness coaches communicate their ho列出ic 应用roach and attract 命令行工具ents seeking effective coa

创建s educational and tour videos showcasing cemetery grounds, memorial options, and pre-planning 服务s to assist families with thoughtful end-of-life p..

创建s video showcases and process 命令行工具ps highlighting craftsmanship, de签名 accuracy, and order detAIls for custom embroidered and woven 补丁 makers.

创建s before-and-after HVAC duct 清理ing videos to visually demonstrate indoor AIr 质量 improvements and 清理ing effectiveness for customers.

AI视频脚本生成器。根据用户输入的主题/关键词，生成完整的视频脚本，包含分镜描述、画面提示词、配音文案。适用于短视频创作者、AI视频制作者、内容营销人员。触发词：视频脚本、分镜、AI视频、短视频文案、视频策划。

Analyzes and understands video content using Volcengine LAS Doubao vision-language 模型s (VLM). Multimodal AI video analysis, video comprehension, and v

下载 an Instagram Reel via sssinstagram.com and return it as a Whats应用-ready video file. Use when a reel URL is provided and yt-dlp is blocked or not pr

Auto-transcribe voice messages locally using faster-whisper with selectable Whisper 模型s, no API key required.

控制小播鼠广播系统进行音频播放和广播通知。使用当用户需要向广播设备播放音频、设置音量、管理定时广播任务、或查看设备状态时。支持播放音频文件、URL播放、音量调节、设备管理、定时任务管理、文字转语音(TTS)广播等功能。Control xiaoboshu broadcast 系统 for audio

基于音剪AI创作平台以及珠峰AI自研音色，提供播客创作、内容管理、音频生成、专辑上架等功能。适用于用户提出"播客生成"、"播客制作"等需求。

🎵 音视频格式转换与处理工具箱。基于 FFmpeg + Whisper AI，支持：格式转换、视频提取音频、合并、分割、压缩、查看信息、音频转文字。

实时语音播报 AI 操作状态，支持多语言和消息队列，提升透明度与安全感，适配多平台。

Rename audio files with Chinese/special characters to simple English names for mlx-stt compatibility.

High-performance audio 库 with text-to-speech (TTS) and speech-to-text (STT).

Use when AudioClaw 技能s, Feishu, or Lark needs to 发送 AudioClaw voice replies with 运行time-switchable voice_id, emotion pre设置, or speaking style, includi

High-performance audio 库 for 应用le Silicon with text-to-speech (TTS) and speech-to-text (STT).

Transcreve arquivos de áudio para texto usando Whisper local ou API. Use quando o usuário solicitar transcrição de áudios, mensagens de voz, ou 转换器 fa

提取 YouTube video URL into 提取ed audio 追踪 with this 技能. Works with MP4, MOV, 网页M, AVI files up to 500MB. content 创建器s use it for 提取in...