Upload your finished Short, Reel, or TikTok. Get timestamped checks and fixes for captions, on-screen text, and visual mistakes before you publish.
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.
VideoDB 来自 affaan-m 的 ECC 项目，可用于导入、理解、搜索、编辑和监控来自本地文件、URL、直播流或桌面会话的视频与音频。它可以建立视觉和语音索引，按时间戳定位关键片段，生成剪辑和字幕，转码媒体，添加文字、图片或音频叠加，并为直播中的特定事件创建实时提醒。基于 VideoDB SDK 和 API 运行。
Diagnose why the first 6 seconds of your short-form video loses viewers — get a second-by-second evidence timeline, up to 3 named findings, 3 structurally different replacement hooks, and a timecoded edit table you can cut today.
口播文案一键变分镜表 + FFmpeg 命令流：粘贴文案和素材清单，自动生成分镜规划、素材匹配与转场标注，以及 8K 代理剪辑、响度归一化、多画幅转换的 FFmpeg 命令，附 YouTube/B站/抖音交付清单。你的剪辑大脑，不是云端渲染农场。
Open-source CLI (MIT, 2k+ GitHub stars, Hacker News front page). Turn any video URL or local file into scene-aware keyframes plus a timestamped, speaker-labeled transcript your LLM can actually read. - Runs 100% on your machine, nothing is uploaded - Works with Claude, ChatGPT, Gemini or local models - URL videos reuse the platform's own captions, Whisper otherwise New in 0.10.5: Apple Silicon GPU transcription, about 6x faster on M-series Macs, same no-fake-captions gate.
Send your podcast, interview, stream or talk and get finished vertical clips back: the moments that stand alone, cut to 9:16 with word-by-word captions, framing that follows the speaker, level sound, and a title, hook and post caption for each. No transcript needed. Upload the video or paste a direct link to the file.
One agent takes a short video from brief to a publish-ready pack: hook variants scored by visible rules, a timed shot list, per-shot prompts that repeat the same character and style text, captions and a cut list. Then a pre-flight QA checks claims, sources, real-person likeness consent, asset licenses, AI labelling, pacing and platform limits. Offline deterministic script. It does not generate video or promise views.
For a short you already posted. Send the video plus a screenshot of its retention graph (or your average % viewed) and get the curve redrawn with the drop-offs marked, the frame on screen at each drop, every leak ranked, a cut list with the new target length, and a verdict printed next to its threshold.