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 a story, dialogue or rough prompt into a complete Seedance 2.5 video prompt. Automatically plan shot sizes, camera positions, framing, movement, focus and cut timing, with character acting, listener reactions, lighting, sound and continuity. Supports text, image and white-model references, centralized asset binding and an exact locked white-model paragraph. Includes prompt-writing skills and optional shot plans; video rendering and model credits are not included.
Turn a script into a vertical narrated short with voice and subtitles that light up word by word. Speech recognition recovers the timings from the generated audio, so captions never drift when you change the voice, the speed, or a line.
Send it a long video link — or an uploaded file. It reads the source, decides by itself which stretch is worth clipping, generates short clips with captions, reviews the results, and delivers only the ones that pass — each with a recommended title, an opening hook and hashtags.
Feeds it raw footage (talking-head clips or silent B-roll) and renders a finished short-form video: punch-in zoom that changes rhythm on every cut, animated captions with numbers and keywords auto-highlighted, a rotating pool of transitions, synthesized whoosh sound effects, and music that auto-ducks under speech. Works with or without subtitles - silent B-roll still cuts on a fixed rhythm instead of sitting static. One Python script, one dependency (ffmpeg), runs fully on your own machine.
读取剧本内容，基于剧本逐集生成分镜脚本，并为每个镜头生成适配 Seedance 2.0 AI 视频生成模型的提示词。融合禅意意境与赛博高级质感，支持已分集和未分集剧本输入，自动根据场景情绪密度切分镜头，输出结构化分镜提示词（含STYLE LOCK、形象视觉锚定、画面描述、HARD CUT、音效设计）。每集 90-120 秒，全片统一真人写实+电影级调色风格。Use when user asks to generate storyboard prompts, 分镜提示词, Seedance prompts, 剧本转分镜, AI视频提示词, 逐镜提示词, 分镜脚本, 镜头脚本.
Your script runs long and you are recording today. Open one HTML file in any browser - no install, no signup, no API key, no coding tool of any kind - and every line becomes a row you can keep, tighten or cut while the running total moves. It names the lines that would get you to your target, strips stock filler and reports what it cost, finds the block eating the overrun, checks a hook against the first seconds, and exports the recut script, caption cards and a printable shot list. Offline.
Turn your own video and matching SRT into source-linked vertical clips: MP4s, editable subtitles, a review page and original time ranges. Render locally with Python and FFmpeg, without a paid video API or per-render service fee. No transcription, URL download or publishing. Review context, caption alignment and audio before posting.
Turn any idea, trend, or win into a ready-to-shoot TikTok / Reels / Shorts script that earns watch time and shares. Built on a proven framework — 12 short-form hook formulas (the first 1–2 seconds), video structures with timestamps, on-screen text and retention rules, and an anti-'AI-slop' voice guide. Get the full script plus 3 hook variations, a caption and hashtags, and a content-calendar generator. Runs with your own model — no extra cost.