Creating your first Cuevo AI explainer video is highly intuitive. We have designed a streamlined 4-step wizard interface for you. Below is the step-by-step walkthrough. Before you begin, all you need is a written script (in Chinese or English, any length) or a ready-made audio/video asset.
Four-Step Workflow Breakdown
Step 1: Script Input
On the Studio page, choose either "Article" or "Audio/Video" mode. If you have a written script, paste it directly into the editor. If you have raw assets (e.g., recorded lectures or speech files), upload them. The system will use ASR to automatically recognize the voice content and slice it into storyboard shots.
Expected Outcome: Once input is saved, the system performs a preliminary analysis on paragraph structure and script length. No points are consumed at this stage.
Step 2: Settings Configuration
Select the following parameters for your video output:
- Aspect Ratio: Landscape 16:9 (for YouTube/Vimeo) or Portrait 9:16 (for TikTok/Reels).
- AI Avatar: Pick an actor from our pre-trained library or use your custom digital clone.
- TTS Voiceover: Choose from 20+ preset timbres, or use cloned voices.
- Host Avatar Photo: Upload a portrait image to serve as the presenter's first-frame visual anchor.
Expected Outcome: Once configured, you are ready to proceed to storyboard generation.
Step 3: Storyboard & Shot Slicing
Click "Generate Storyboard". The orchestration engine automatically slices your text into shots and assigns a visual intent (A-Roll / B-Roll / VFX Card), script text, and a visual description prompt. You can tweak or rewrite prompts anytime. Use double brackets [[word]] to overlay synchronized floating keywords, or specify rich-card types to insert any of the 16 VFX templates.
Expected Outcome: You will see a complete storyboard shot list, estimated duration, and thumbnail previews. Click any shot to edit it in detail.
Step 4: Final Rendering
Confirm all shots, then click "Start Render". The system processes shots in parallel on cloud GPU clusters, showing real-time states (Queued / Rendering / Completed / Failed). Upon completion, shots are stitched into a complete video. Preview each shot, and click "↻ Re-generate" to retry individual shots if necessary.
Expected Outcome: You get a complete AI digital presenter video (MP4) to download or share. If you only want to adjust global properties like BGM or watermark, use "Re-synthesize" without re-rendering the whole timeline.
💡 Pro Tip
Your account is refueled with free points daily. A 15-shot short video consumes about 100-200 points. The 500 daily free points are sufficient for beginners to explore the studio features. If you need more points, wait for the next day's refresh or check out upgrade packages in the User Center.