
Turn your ideas into short-video scripts, shot-by-shot storyboards, copy-ready AI video prompts, and editing checklists. Plan product demos, social videos, and image-to-video projects in English. Created by the team behind Flow AI Video: https://flowaivideo.org/. This assistant plans videos; it does not render them.

Turn one idea into a short-form video production plan with a script, shot timings, text storyboard, AI visual prompts, captions, titles, and A/B variants. No finished MP4 included.

把附出处的稿件变成完整的 16:9 解说视频或新闻回顾:旁白、字幕、跟随旁白切换画面的图片场景、章节、配乐、封面、YouTube 说明栏,另附 .srt 字幕文件。旁白支持英语、普通话(繁体或简体字)及粤语。在制作每周 AI 新闻视频系列的过程中开发和打磨。

Turn one product, topic, character, image, or rough script into a ready-to-paste 9:16 AI video prompt pack: hook, scene flow, camera moves, narration, on-screen text, captions, hashtags, and posting checklist for TikTok, Reels, and Shorts.

把短剧剧本或剧情片段,拆成可执行的专业拍摄脚本、人物/场景/道具图片生成提示词、16:9导演分镜工作板和 Jimeng/Dreamina 视频提示词。适合AI短剧创作者、导演、编剧和视频团队,重点解决剧情被改写、人物站位混乱、道具连续性丢失、分镜与视频提示词不一致、演员表演空、镜头语言太泛、上下CUT衔接断裂等问题。

Plan children's videos with AI-assisted story scripts, character profiles, scene-by-scene text storyboards, narration and dialogue drafts, and prompts for external image and video tools. Includes YouTube content planning, Shorts outlines, and series ideas. Important: This is a text-based planning toolkit, not a video generator. No finished videos, MP4 files, images, voice recordings, or music files are included. External production tools are required and may cost extra.

Download package that runs on your own computer inside your AI agent (e.g. Claude Code or Codex — that agent's subscription/API costs are yours). Requires Python 3.9+, ffmpeg and faster-whisper (free; 150–500 MB model download on first run). You supply the footage: it transcribes locally, your agent picks self-contained moments, and the scripts cut 9:16 clips with word-timed captions, a hook banner, titles and hashtags. No other third-party services or keys.

Paste a short script and get 6-12 self-contained AI-video clip prompts with a continuity anchor block, four reviewer lenses and a regenerate-first list.