How to create videos

Use this guide to set up a project and produce videos manually from the dashboard: Projects → Videos → publish. Configure creative settings once per channel or niche; the same settings apply to every video in that project (including Auto Mode later). For hands-free scheduling and posting, finish project setup here first, then follow Automatic video generation.

Create a project

In the dashboard, open Projects and click Create Project. Your first project uses a short wizard: enter Title and Channel Description, then continue to full settings. For later projects, the configure modal opens with all sections at once. Use Configure on any row to edit an existing project.

Project settings

Everything below lives in the project configure modal (Create Project / Configure). Match labels in the app when you look for a field.

Basics

Title
Channel or niche name for your reference in Projects and Videos.
Content Types
Select one or more types. The AI mixes segment types within each video.
Video orientation
Vertical (9:16) for Shorts/TikTok (target up to 2 minutes). Landscape (16:9) for widescreen (target up to 15 minutes).
Channel Description
Required, 100–5,000 characters. This is the main creative brief for ideas, screenplays, and visuals.
Output format
For projects using only AI Images and/or Web Images: Video or Slideshow. Slideshows use a Number of slides setting instead of target duration.

Content type options:

AI Video
AI-generated motion clips per scene.
AI Images
Slideshow-style scenes from AI images.
Stock Videos
Licensed stock footage segments.
AI Influencer
A lip-synced presenter; Reference Image is required. Choose a mode: Talking-head scenes, Avatar overlay only, or Scenes + overlay.
Web Pages
Screen-style segments from web pages; enable Web search in project settings.
Web Images
Segments built from web-sourced images.
Code Animations
Generated motion-graphics animations for abstract, data, and process beats; falls back to stock footage if a render fails.
Uploaded Media
Your own footage and images (up to 10 files per project; videos max 3 minutes / 200 MB, images max 25 MB). Analysis starts automatically after each upload and costs 1 credit per started video minute (1 credit per image) so the AI can cut any moment or still into scenes.

Slideshows

When your content types are exclusively AI Images and/or Web Images, an Output format choice appears: Video or Slideshow. Slideshow projects replace Target Video Duration with Number of slides (2–10; default 5). The AI writes a short text line for each slide, baked onto the image with your caption styling. You can review and edit each slide's text on the video page; use Update slides to re-bake the images (exporting also re-bakes, and TikTok posts the baked images as-is). Prefer no text? Choose None under the slide text styles in project settings and the slides render without text.

TikTok receives a native photo carousel and automatically adds a recommended music track from TikTok's library — you can change the track later in the TikTok app. YouTube receives the same slides rendered as a short video with your project music. The narrator is off for slideshows; they are music-driven.

Reference Image

Optional for most projects; required when AI Influencer is enabled. Upload a clear portrait of your presenter (crop matches project aspect ratio). It defines the presenter identity for talking-head scenes and for the circle avatar overlay. See AI Influencer avatar overlays.

Ideas and web search

Web search uses real-time web data when generating titles, transcripts, and full ideas (3 credits per step instead of 1). Required for Web Pages content. Ideas per batch controls how many titles are generated at once (3–10; default 10). Lower values (e.g. 3–5) keep Auto Mode fresher for news or timely topics.

Voice

Use narrator voice adds spoken narration (xAI, Speechify, or ElevenLabs) and is on by default on new projects. It can be turned off for any content type; it is forced on for AI Influencer (scene speech drives lip-sync and the avatar overlay) and forced off for slideshows (music-only). Pick a voice and adjust narrator speed (1.0–1.2; xAI and Speechify only — ElevenLabs v4 ignores speed).

Video

Target Video Duration (seconds)
10–120 seconds for portrait; 10–900 seconds for landscape. Drives screenplay length and generation cost. Not used for slideshows; those use Number of slides instead.
AI Influencer mode
Talking-head scenes, Avatar overlay only, or Scenes + overlay. Overlay modes require at least one other visual content type.
Image models (priority)
Pick 1–4 models in order; the next model is tried if one fails. Used for AI Video frames, AI Images, and related segments.
AI Video models (priority)
When AI Video is enabled: 1–3 video models in priority order (e.g. Grok, Veo, Sora).
AI Influencer models (priority)
When AI Influencer produces talking-head scenes: 1–3 lip-sync models in priority order.
Generate cover photo
Optional thumbnail/cover per export (uses credits; can be used as YouTube thumbnail when posting).
Background music & sound effects
Optional music under narration; optional short SFX on certain scene transitions.
On-screen text / caption preset
Full captions, sparse highlight titles, or none — plus a visual preset when captions are on.
Watermark
Optional branded watermark on exports (position and opacity in the watermark editor).

Channel description tips

Describe your topic, audience, structure, visual style, and tone. Include example titles or hooks. A strong description improves both manual ideas and Auto Mode output.

From idea to finished video

Generate video ideas

Go to Videos and click Generate Video Ideas. Pick your project and confirm. VidMachine creates a batch of titles from your channel description (1 credit per batch; batch size is set in project settings).

Pick an idea and generate the video

Open an idea from the list and use Generate Video to run the full pipeline: idea expansion, screenplay, segments (AI video, images, stock, web, influencer, etc.), optional narrator, captions, and export. Generation uses credits based on length and models.

Schedule or publish

When the video is ready, set status to Upcoming with a post time, or publish immediately. Connect YouTube and TikTok (and Instagram Reels when available) under Accounts in the sidebar. For fully automatic creation and posting, use Schedule settings on the project — see Automatic video generation.

Credits and generation time

Video generation, narrator, captions, and covers consume credits. Cost depends on duration, content types, and model choices. See Credits & billing. Generate Video queues work immediately — you can leave the page. The Videos list shows status (queued, processing, draft, error, etc.).