OpenClaw AI 技能

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。

🎵 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。

Skip the learning curve of professional editing software. Describe what you want — 移除 all audio from this video and 导出 it silent — and 获取 silent MP4..

Analyze audio recording 质量 - echo 检测ion, loudness, speech intelligibility, SNR, spectral analysis. Use when the user wants to 检查 a recording's 质量, 检测

当用户想要**把长音频切成小段**、**音频切片**、**音频分割**、**把音频分成固定时长片段**、**制作语音数据集**、**准备Karaoke素材**、**翻唱音频切片**时自动触发。 支持单个音频文件或整个文件夹（支持递归），自动用 ffmpeg 把音频按指定秒数切成小片段，完美保留原始

Analyze audio 质量, 检测 noise types, and provide improvement recommendations. Use when users need to 检查 audio 质量, 验证 recordings, or identify audio proble

Offline speech-to-text (ASR) using whisper.cpp (whisper-命令行工具) + ffmpeg. Supports batch transcription, timestamps, SRT/TXT/JSON 输出s, and 模型 下载. Cr...

生成 speech from text using KyutAI Pocket TTS - lightweight, CPU-friendly, 流ing TTS with voice cloning. English only. ~6x real-time on M4 MacBook AIr.

Transcribe or translate audio files to text using a public Hugging Face Whisper Space over Gradio. Use when the user 发送s voice notes, audio attachment

Automatically converts speech messages in ogg/wav/mp3/m4a 格式化s to text using offline Faster-Whisper with ffmpeg 格式化 conversion.

本地视频理解技能，利用ffmpeg提取音频和帧，FunASR进行语音识别，qwen3-vl进行图像理解。

生成完整的Amazon商品列表草稿，包括标题、项目符号、图像计划、提示和视频脚本。

主动的中文语言导师，按照时间表提供精选的真实世界的普通话学习内容。使用时机：（1）用户想要学习或提高中文/普通话。（2）用户询问中文阅读材料、播客、视频或歌曲推荐。（3）通过cron/heartbeat触发定时课程推送。（4）用户说“中文课”、“Chinese lesson”、“teach me C

Task Director — turn complex tasks into movie storyboards. 创建 a plan, review it, then 执行 step by step with fallback support. 暂停, retry, skip anytime.

Complete Google NotebookLM integration — 添加 sources, ask questions, 生成 all Studio content (podcast, video, slide deck, quiz, flashcards, 信息graphic,...

发送 native voice bubbles via Feishu using edge-tts + ffmpeg. Converts text to OGG/Opus audio and 发送s as a playable blue voice bubble. Use when: (1) Use

生成 SenseAudio TTS narration 追踪s for videos, including timestamped segments, style variants, and editor-ready voiceover 导出s. Use when users need voiceo

Record video proof of implemented features after coding tasks complete. Use when a coding 代理 finishes work and needs to visually 验证 and demonstrate th

Record video proof of implemented features after coding tasks complete. Use when a coding 代理 finishes work and needs to visually 验证 and demonstrate th

MiniMax Text-to-Speech synthesis using the HTTP REST API. 生成s high-质量 audio from text in 40+ languages with ultra-rea列出ic voices. Use when the user wa