Secrets AI Video Generator: How It Works, Quality, and Cost

Video generation from AI companion images is genuinely rare in this market — and it is Secrets AI's most distinctive feature. Character.AI does not offer it. CrushOn AI does not offer it. Janitor AI does not offer it. Candy AI has limited video capability. Secrets AI generates short video clips from your companion's images using a text prompt, and the results earn a 4.1/5 quality rating from independent reviewers.

This page covers how the video generator works step by step, what quality to realistically expect, the full cost breakdown in Moments, and how to get the best results from your Moments budget.

For platform pricing and Moments allocation by tier, see the full pricing breakdown. For an overview of all platform features, visit the features page.

What Is the Secrets AI Video Generator?

The video generator converts existing AI companion images into short animated video clips using a text prompt that describes the desired movement or action. It is built into the core platform — no external tools, no third-party services, no separate subscription.

Key facts:

• Available from Lite tier and above — free accounts cannot generate videos
• Generates clips directly from your companion's visual appearance
• Uses the same character consistency as static image generation
• Produces context-aware output reflecting the conversation scenario
• Output is a downloadable/viewable video clip

The feature's rarity in the AI companion category is significant. Most platforms in this space focus on static images for visual content — the technical complexity of video generation is higher, and many platforms have not invested in it. Secrets AI's decision to include video as a core feature rather than an add-on positions it distinctively for users who want dynamic visual content from their companion.

How Video Generation Works

The process follows four steps:

Step 1: Generate or select a companion image

Video generation starts with an image. You can use one of the four auto-generated images created when you built your character, or generate a new image (25-50 Moments). The quality of the source image directly affects the quality of the video output — use the best available image.

Step 2: Add a text prompt describing the motion

Write a prompt describing what movement or action you want the character to perform. Specific prompts produce better results than vague ones. "Smiling softly and tilting head to the right" will generally produce better output than "look at me." Keep prompts focused on achievable physical movements — the video generator handles facial expressions, head movements, and body motion well.

Step 3: Wait for generation (~2 minutes)

The AI processes the request and generates the video clip. Average generation time is approximately 2 minutes. This is consistent — you can initiate a video, continue chatting, and check back when it is ready.

Step 4: View and save the completed clip

The finished video clip appears in the interface for viewing and saving. Short clips (3 seconds) are available from Lite tier; longer clips are available from Plus and above.

Video Quality Assessment

Independent reviewers rate Secrets AI video quality at 4.1/5 — the second-highest feature score on the platform (voice calls edge it out at 4.3/5).

What that rating reflects in practice:

• Smooth movement: The majority of generated clips have natural-looking motion without jerky transitions or unnatural body mechanics
• Facial expression quality: Expressions render well in most outputs — smiling, different emotional states, and reactive expressions are handled realistically
• Character consistency: The generated video accurately reflects the character's appearance as defined in your setup
• Prompt responsiveness: Specific, well-crafted prompts produce results that match the intended action reliably

Where quality varies:

• Very complex physical actions (multiple simultaneous movements, full-body action sequences) produce less consistent results
• Prompt complexity has diminishing returns — very long, multi-part prompts can confuse the generation
• The Advanced generation model (available on Premium tier) produces noticeably better video quality than the standard model

Reviewers note that while video quality is good-to-excellent for typical companion interactions, it does not match the quality of purpose-built AI video tools like Runway or Kling. The value is the integration within the companion platform — not standalone video production capability.

How Much Do Videos Cost in Moments?

Video is the most Moments-intensive feature on the platform.

For comparison:

For the same 600 Moments: 1 full video OR 12-24 images OR 6 minutes of voice.

Monthly video budget by tier:

These are maximum video estimates — in practice, most users mix video with images and text messages, reducing the number of videos produced per month.

Key takeaway: If video is your primary use case, the Moments system makes Lite and even Plus feel constrained. Premium (8,000 Moments) provides a workable budget for regular video use. Ultimate (15,000 Moments + 15% top-up bonus) is the practical tier for heavy video creators.

Additional Moments can be purchased separately in bundles from 1,980 Moments ($5.99) up to 118,800 Moments ($249.99), with per-Moment costs decreasing as bundle size increases.

For a full discussion of which tier to choose based on your intended use pattern, see the free vs premium comparison.

Tips for Better Video Results

These practices consistently improve output quality:

• Use high-quality source images: The video generator produces better output from sharper, well-lit source images. If the source image has quality issues, the video will inherit them. Regenerate your source image using the Advanced model if available before converting to video.
• Write specific, focused prompts: "Turns head slowly to the left with a gentle smile" outperforms "look at camera." Describe single, specific physical actions rather than complex multi-part sequences.
• Test with short clips first: Short 3-second clips (~50 Moments) let you evaluate quality for a given prompt before committing up to 600 Moments on a longer version. If the short clip works well, scale up.
• Use Premium generation model: Available on Premium tier, the Advanced generation model is noticeably better for video output — smoother motion and better facial expression rendering.
• Match prompts to your conversation context: Videos that match the established scenario and the character's personality tend to produce more contextually coherent results than prompts disconnected from the conversation thread.
• Save good source images before converting: Once you have a companion image that renders particularly well, save it for future video use rather than regenerating each time.

Who Should Use the Video Generator?

Worth prioritizing if:

• Visual content is a significant part of why you want an AI companion platform
• You want companion media beyond static images — dynamic, animated content that brings the character to life
• You are on a tier with enough Moments to generate video without depleting your budget prematurely (Plus or above recommended)
• You enjoy saving or revisiting companion content

Not the core use case if:

• You are primarily a text-focused companion user — video Moments costs are high relative to the conversational value
• You are on a tight Moments budget and need to prioritize image and text
• You are on the Free tier (no video access)

Recommended tier by use intensity:

• Occasional video (1-5 clips/month): Plus ($9.99) covers this comfortably within 3,000 Moments
• Regular video (5-15 clips/month): Premium ($19.99) with 8,000 Moments handles this sustainably
• Heavy video use (15+ clips/month): Ultimate ($39.99) with 15,000 Moments + 15% top-up bonus is the practical choice

Competitors with Video Generation

The AI companion market's video generation landscape:

Among mainstream AI companion platforms, Secrets AI's video generation is genuinely distinctive. Xotic AI offers high-resolution 15-second clips as a competitor worth knowing about; SweetDream AI has limited video capability. For the vast majority of platforms in this space, video generation is simply not available.

This matters when comparing Secrets AI against alternatives: if video is a priority, the choice set narrows significantly. For a full competitive comparison, see the alternatives guide.

FAQ