Q&A · Answers from real-world tests on X

How to make videos with Codex?

Not in your language? Paste the link or the text into your AI and let it read it for you.

8 source posts · 8 creatorsLast updated Nov 1
Short answerBased on hands-on tests in the posts, people using Codex to make videos generally install a Skill (skill package) and then have it edit or assemble the video. Talking-head videos can be auto-edited with a JianYing-related Skill. If you don't want to appear on camera, you can make a hand-drawn whiteboard video. To replicate viral videos, you can try the open-source Hypit. Some also have Codex operate Blender to generate animations. Below, these are covered by use case, starting with talking-head editing, the easiest to get started with.

How to do it

Click an avatar to see the source post
  1. 1

    For talking-head videos, you can install Yichen's open-source JianYing Skill and hand it to Codex with a single prompt. The author's test: an 8-minute raw clip was automatically cut down to 3 minutes, with segments trimmed down to the millisecond.

  2. 2

    The output is a native JianYing draft, including multiple tracks, subtitles, and volume levels. You can fine-tune it manually in JianYing, or export an MP4 headlessly in the background.

  3. 3

    Doubao voice recognition costs about 0.8 yuan per hour. Some say the Codex token costs can be replaced by using a cheaper model.

  4. 4

    If you don't want to appear on camera, you can use Codex plus Excalidraw to make a hand-drawn whiteboard video from a single sentence. The author says the Skill is open source, and after cloning it, you can produce your first video in ten minutes.

  5. 5

    To replicate a viral video, you can use the open-source Hypit. Give the reference video to Codex, break it into editable components, then swap the host, topic, and language to produce multiple versions in batches.

  6. 6

    There are also two editing Skills to choose from. Pireel focuses on talking-head scenarios and installs with one line in Codex. BaoCut can transcribe, translate, and do simple editing, but it only supports Mac.

What people on X saySorted by usefulness

01逸尘09-18ZHJianYing Open-Source Skill Plus Codex Fully Automates Talking-Head Video Editing#1把我珍藏已久的好东西分享给家人们,剪映11.4.2开源!!!🥳🥳🥳https://t.co/CGXDq1tcIh 配套神级Skill:https://t.co/QQ5XDF75mwCodexImageOriginal post1.2MLikes 3.6K
02余温09-18ZHCodex Operates JianYing Headlessly, Generates a Native Draft, Then Exports#2wtf,这神人居然把剪映给逆向了??? 直接 Codex 无界面操作剪映,这是真不怕收到律师函啊😂 笑死我了,前几天还私聊跟我说至少卖 888 一份。CodexImageOriginal post535KLikes 2.6K
03Simon聊AI09-24ZHCodex Plus Excalidraw Makes a Whiteboard Video From One Sentence#3Codex + Excalidraw,一句话出一条手绘白板视频,这套我自己用下来真的香 不露脸,不剪辑,高质感CodexOriginal post249KLikes 995
04超级个体09-15ZHHypit Lets Codex Clone Viral Videos and Batch-Swap Hosts卧槽,这不就是 AI 时代的合法印钞机吗??? 几分钟复刻任何!!任何!!爆款广告片,视频,街头采访……等等 换个脸换个话题,批量出 100 条同类爆款视频??你这让苦苦研究选题脚本的编导还活不活了?CodexImageOriginal post268KLikes 1.3K
05tangjinzhou07-22ZHPireel Video Editing Skill Installs in One Line in Codex一个吃过开源红利的人, 靠开源挣了 300 万左右, 现在却一头扎进闭源项目里——你说傻不傻? 很多人认识我,是因为开源项目 Ant Design Vue。它始于 2017 年 9 月, 到今天累计收获了 22K Star(加上周边项目有 50K)。CodexImageOriginal post152KLikes 605
06宝玉07-15ZHBaoCut Skill Transcribes, Translates, and Cuts Verbal Tics, Mac Only字幕转录翻译剪辑 Skill —— BaoCut(仅支持 Mac) 借助 Agent Skill,可以转录视频、对转录结果识别 Speaker、润色(纠正错别字口癖等)、也可以根据转录结果对视频进行简单的剪辑,比如删除口癖、重复等。CodexImageOriginal post160KLikes 508
07狗哥笔记07-15ZHFull Workflow and Checkpoints for the Codex Collage Animation B-Roll Skill拼贴动画 B-roll Skill 正式开源🔥 评论区可见 👹整个工作流程如下: 1、Codex skill 安装与首次环境自检(缺什么教你配什么) 2、一句口播文稿 → 压成一个视觉隐喻:核心意思、关键物件、底色、组装顺序CodexImageOriginal post233KLikes 802
08歸藏09-05ZHGPT-6 Operates Blender for Animation: Cost Comparison With Video Models做一个实验,用 GPT-6 操纵 Blender 生成的动画,和现在最强的视频模型 Seedance 2.5 1080P 生成的动画进行对比。CodexImageOriginal post222KLikes 751
No matching posts or creators found

Everything here comes from real-world tests by users on X. Rules and products change often, so always check the latest. If you know a better way, we'd love to hear it.

Related questions

How do you write AI image-generation prompts?7 postsView all 13 questions