Secrets AI Video Generator: How It Works, Quality, and Cost
Most AI companion platforms do not have video generation. Secrets AI does. Here is what it produces, what it costs, and whether it is worth the Moments.
What Is the Secrets AI Video Generator?
The video generator converts existing AI companion images into short animated clips via a text prompt. You provide an image and describe the movement or action you want — the system produces a video clip showing your companion in motion.
This feature is genuinely rare in the AI companion market. Competitors including Character.AI, CrushOn AI, Janitor AI, and most smaller platforms offer no video generation capability at all. Of the platforms that do, the Secrets AI implementation is among the most accessible — it requires no external tools, no separate subscription, and runs within the same interface as the rest of the platform.
Video is available from Lite tier ($5.99/month) and above. It is not accessible on the free plan. For the broader platform context including chat, image, and voice features, see the complete features guide.
How Video Generation Works
The process is four steps:
- Select an image. Use an existing companion image from your library — either one of the 4 auto-generated images from character creation or a previously generated image. The quality of the source image directly affects video output quality.
- Write a text prompt. Describe the desired movement or action. Specific prompts produce better results than vague ones — "turn and smile while walking toward the camera" produces better output than "move around."
- Wait for generation. The system processes the request in approximately 2 minutes. This is not real-time — you submit and wait, similar to image generation with a longer processing window.
- View and save the output. The completed clip is displayed in the interface. Save it if you want to keep it.
Clips range from 3 seconds on Lite tier to longer durations on higher tiers. The AI uses deep learning and image generation technology comparable to systems like Stable Diffusion to produce movement from a static source image. The context of your conversation and character appearance is reflected in the output.
Video Quality Assessment
Quality is rated 4.1/5 by independent reviewers — the platform's second-highest feature rating after chat quality (4.4/5).
In practice:
- Movement is smooth and natural in most outputs
- Facial expressions reflect the emotion described in the prompt
- Character appearance is consistent with the source image
- Occasional quality variations occur based on prompt complexity and source image quality
- Prompts requiring complex multi-person movement or highly specific gestures produce more variation
The Premium generation model produces better quality than the standard model. If you are generating video and have access to the Premium model (Premium tier and above), use it.
The "4.1/5" rating is honest — it is not perfect. Short clips on simple prompts reliably produce clean output. Complex prompts on longer clips introduce more variation. Starting with short test clips on simple prompts is the recommended approach for first-time use.
How Much Do Videos Cost in Moments?
| Video Type | Moments Cost |
|---|---|
| Short clip (3 seconds) | ~50 Moments |
| Standard clip | ~200–400 Moments |
| Full-length clip | ~600 Moments |
Video is the most Moments-intensive feature on the platform. For reference:
| Feature | Moments | What You Get |
|---|---|---|
| Text message | 1–2 | One AI response |
| Image | 25–50 | One static image |
| Short video (3s) | ~50 | Brief motion clip |
| Full video | ~600 | Longer motion clip |
| Voice call | 100/min | Real-time audio |
For the same 600 Moments spent on one full video, you could alternatively generate 12–24 images, or make 6 minutes of voice calls, or send approximately 300–600 text messages.
Monthly Video Budget by Tier
| Plan | Monthly Moments | Short Clips (~50 each) | Full Clips (~600 each) |
|---|---|---|---|
| Lite | 1,000 | ~20 | ~1–2 |
| Plus | 3,000 | ~60 | ~5 |
| Premium | 8,800 effective | ~176 | ~14 |
| Ultimate | 17,250 effective | ~345 | ~28 |
These are pure-video numbers — real usage mixes text and images, which reduces the video count. On Premium with realistic mixed use (images + text + some voice), expect 5–10 full videos per month within budget. Ultimate is built for heavy video use.
Tips for Better Video Results
Practical improvements based on how the system works:
- Use high-quality source images. The video generator enhances what it starts with. Blurry, poorly lit, or awkwardly posed source images produce worse video output. Generate a few images and pick the best one before converting to video.
- Be specific in your prompt. Describe the movement, direction, and emotional context. "Walk slowly toward the camera with a smile" produces better results than "walk." Emotion in the prompt (happy, playful, sensual) influences facial expression output.
- Test with short clips first. At ~50 Moments per 3-second clip versus ~600 for a full clip, testing your prompt on a short clip before committing to full length saves significant Moments. If the short version looks good, proceed to full length.
- Use the Premium generation model. If your tier includes the Premium model, select it. The quality difference is noticeable on longer clips with complex movement.
- Generate images first, then video. Images at 25–50 Moments each are cheaper. Create several variations of your companion's pose and appearance, then convert the best result to video. This approach is more efficient than generating video directly from prompts.
- Keep prompts realistic. The system handles natural human movement well. Very complex physics (water, fabric, multiple interacting people) introduces more variation.
Who Should Use the Video Generator?
Worth it if:
- Visual content is a priority alongside chat interaction
- You want unique media from your companion
- You are on Premium or Ultimate with sufficient monthly Moments
- You value the creative aspect of directing your companion's movements
Not worth it if:
- You are primarily text-focused — the Moments cost does not deliver proportional value
- You are on Lite tier — 1,000 Moments limits you to 1–2 full clips per month
- You are in your first month evaluating the platform — use the 200 free Moments and Lite tier for text before committing to video costs
Best tier for regular video use: Premium ($19.99/mo) for moderate use (5–10 full clips monthly). Ultimate ($39.99/mo) for heavy use (25+ full clips monthly, or sustained short-clip generation).
Competitors with Video Generation
The absence of video generation on competing platforms is the clearest differentiator for Secrets AI:
| Platform | Video Generation |
|---|---|
| Secrets AI | Yes — image to video |
| Candy AI | Limited |
| CrushOn AI | No |
| Character.AI | No |
| Janitor AI | No |
| SweetDream AI | Limited |
| Xotic AI | Yes (4K, 15-sec clips) |
Character.AI — the largest AI companion platform by user count — has no video generation. CrushOn AI and Janitor AI, the two most prominent budget alternatives, have no video generation. Only specialty platforms like Xotic AI (which offers higher-quality 4K 15-second clips) are competitive in this specific capability.
This is a genuine market differentiator, not marketing language. If video generation from AI companion images is a priority in your platform selection, Secrets AI is one of very few options at this price point.
The full review covers all platform features and the overall value assessment.
FAQ
Video length depends on your subscription tier and the Moments you spend. The minimum clip length is 3 seconds (available from Lite tier at ~50 Moments). Longer clips are available on higher tiers and cost proportionally more — up to ~600 Moments for a full-length clip. Exact maximum length is not publicly documented by the platform; the 600-Moment full clip represents the top end of the pricing range.
No. Video generation requires Lite tier or higher. The free plan provides text-only chat, a one-time 200-Moment allocation (not enough for video at 50–600 Moments per clip in any case), and character library access. To access video generation, you need at least the Lite plan at $5.99/month. See the free vs premium comparison for what each tier unlocks.
It depends on your tier and clip length. On Plus (3,000 Moments): roughly 5 full-length clips or up to 60 short clips (3 seconds each) if your entire allocation goes to video. On Premium (8,800 effective Moments): approximately 14 full clips or ~176 short clips. In practice, most users mix text, images, and video — so actual video count will be lower. The detailed pricing guide shows the Moments math across all tiers.
Yes, generally. Independent reviewers rate video quality at 4.1/5. Movement is smooth and natural in most outputs; facial expressions reflect the emotion described in the prompt; character appearance is consistent with the source image. Quality varies somewhat with prompt complexity — simple movement prompts produce cleaner results than complex multi-element scenes. Using the Premium generation model and high-quality source images improves output consistently.