技能列表

Generate SenseAudio TTS narration tracks for videos, including timestamped segments, style variants, and editor-ready voiceover exports. Use when users need voiceovers, video narration, timed commentary, or accessibility narration.

Guide staged text-to-video generation from a rough user idea to ranked video type options, parameter tuning, prompt preview, and final Volcengine Ark video generation via bundled helper scripts. Use when a user wants help deciding video style, duration, ratio, motion, or prompt wording before generating a video, and when a reusable multi-turn workflow with simple state tracking is needed.

使用火山引擎 SD1.5pro API 生成视频。支持文本到视频和图生视频，异步处理任务。

AI Video generation toolkit — generate videos from text prompts or input images using multiple AI models (Veo 3.1, Veo 3, Seedance 1.5 Pro, Wan 2.5, Grok Imagine Video, etc.). Support both text-to-video and image-to-video generation. Use when users ask for video creation, AI video, text to video, image to video, animate image, video generation.

视频生成技能，使用 MiniMax 视频生成 API 创建视频

Create AI videos with Sora 2, Veo 3, Seedance, Runway, and modern APIs using reliable prompt and rendering workflows.

Extract frames or short clips from videos using ffmpeg.

Download videos and torrents to cloud storage. Requires python3.12, rclone (115-fork, installed to ~/.local/bin), yt-dlp, and aria2c. Install via scripts/install.sh (installs all deps to user directory, no sudo; may append ~/.local/bin to PATH in shell profile). Writes credentials to ~/.config/rclone/rclone.conf (115 Pan, chmod 600) and ~/.config/video-fetch/quark_cookie.txt (Quark cookie, chmod 600) — stored locally only, never transmitted to third parties. Supports 115 offline download (server

Video editing operations using ffmpeg. Use when user needs to: (1) Cut/trim video clips, (2) Merge/join multiple videos, (3) Convert video formats, (4) Extract audio from video, (5) Add subtitles or text overlays, (6) Adjust video speed, (7) Resize/crop video dimensions, (8) Apply filters or effects. Supports common formats like MP4, MOV, AVI, MKV, WebM.

Validate single video URLs, download highest-quality files with yt-dlp, and archive results into a Feishu Bitable using platform tools.

下载视频并用AI分析内容 - 支持B站/抖音/YouTube等平台，提取语音内容并分析视频结构

Video call the user with a real-time AI avatar powered by Runway. The agent initiates calls to the user — for standups, urgent alerts, check-ins, or any conversation that's better face-to-face.