Creating Your First Video
Open Create Video from the app sidebar. Fill in the form, click Next, then walk the style wizard. Some formats skip steps. After one video, save the style as a template so the next job only needs a title and prompt.
1. Fill in the create form
Leave Use a saved template on None — start from scratch for your first video.
- Duration — target length (for example 6–8 or 10–12 minutes). A custom script or uploaded voiceover sets duration from the file instead.
- Format — the video style. Faceless Documentary is the default when that format is enabled. See Video Formats.
- Every video exports as 16 by 9 YouTube landscape.
- Language — narration language.
- Auto (paid) — on skips script review; off adds a Review Script step. Free accounts always run Auto on. See Auto Mode.
Title — at least 3 words.
Reference video (optional) — a YouTube URL whose style Cliptude should match. See Reference Video.
Describe your video — the prompt. Aim for 200–30,000 characters (spaces excluded) unless you attach a script or voiceover. See Prompting.
"A documentary about the history of coffee, starting from Ethiopia to modern day espresso culture, with a calm and informative tone."
Under Enhance with (optional) you can Add Script, Upload Voiceover, or Upload Talking Head instead of a prompt. Then click Next.
2. Walk the style wizard
For the default Faceless Documentary format, the wizard after the form is:
- Select Model Tier — Cinder or Caldera. This is not on the create form.
- Voice Over Selection — pick a catalog voice, clone (paid), or skip this step if you uploaded a voiceover.
- Choose a look — a Faceless Documentary tone pack (Default, News, Yellow, Maroon, Investigative, Dramatic) plus primary and accent colors. Classic Documentary / Top 10 B-roll use a Visual Theme step instead (Standard, Crime, History, and so on).
- Background Selection — library, favorites, or upload.
- Background Music — none, a library track, or an uploaded file.
- Visual Enhancements — charts, animations, and B-roll text overlays.
- Select Style Reference — a YouTube thumbnail, custom URL, or upload that Cliptude uses as the visual reference. This step also shows the credit estimate. A faceless documentary on Cinder costs 22 credits per minute with your own voiceover and 40 with ElevenLabs; Caldera adds 5.
Illustration, explainer, music, and 3D formats insert their own character / style screens and may skip music or enhancements. Keep clicking Next / Continue until Generate Video.
Choose a look
Faceless Documentary uses a tone pack and primary/accent colors — not Visual Theme. See the packs, color roles, and optional custom hex on the look guide.
3. Generate and wait
Click Generate Video. The Progress page shows pipeline status. Generation is not instant — see Rendering Times and The Queue System. When it finishes, the video is in Library. Open the timeline editor if you want to trim, swap footage, or regenerate voiceover. When the cut is ready, Render bakes a new MP4.
4. Save as a template
Once voice, style, music, and thumbnail are set, click Save as template on the Thumbnail step, Progress, or Library. Name it — that snapshot is reused for later videos. You can also create a blank template from Saved Templates and fill the editor there.
Next time on Create Video, pick the template under Use a saved template, add a new title plus prompt (or script / voiceover), and continue. Style comes from the template; you still choose a thumbnail for that job. Full create / edit / delete steps are in the Saved Templates guide.
Or make it from Claude or ChatGPT (MCP)
Connect the Cliptude MCP server (https://mcp.cliptude.com/mcp) to Claude, ChatGPT or another agent and
ask for the video in plain words. In Claude and ChatGPT, Cliptude's tools open pickers and cards inside the chat.
This is the order the agent follows:
- Your templates first.
list_templatesshows your saved templates as a gallery. Pick one. - No template fits? The agent builds one with the pickers, one at a time: voice, then the presenter (Avatar Video) or character (Vector Explainer), then music, background and style.
- Type next. In Claude a click saves your pick and the picker says
"Saved. Type next in the chat to continue." Type
nextand the agent reads it. In ChatGPT the pick is sent as your next message. - Script. The agent researches the topic, writes the script and lets you read it.
- Review card. Every setting, any warnings, a checkbox for anything you turned off, and the credits, with an Every setting tab and a Script (N words) tab. Nothing is built or charged until you click Confirm.
- Job card, then the publish kit. A job card shows progress and, when the job waits for it, the script to approve. When the video is ready, the publish kit plays it and gives you thumbnails, titles, a description, chapters and tags to copy.
Make me a 10-minute [Faceless Documentary / Faceless Top 10 / Avatar Video / Vector Explainer] about [topic]. Show me my saved templates first and let me pick one. If none fits, set one up with me using Cliptude's pickers, one at a time (voice, then the presenter or character, then music, background and style). Write the script, let me read it, and show me the review card before you build anything. Show me the publish kit when the video is ready.
Claude Code, Codex, Cursor and other agents that show no widgets give you a cliptude.com/pick link with the same
picker instead. It works once, for 15 minutes, and only
for you when you are signed in. The agent reads the result with get_pick. From a terminal:
cliptude pick <pick_id> --url <link> opens it and waits.
Setup for each agent: Claude, ChatGPT, Claude Code, or any other MCP agent.