Creative Reality Beginner

The Creative Reality Studio is D-ID's flagship web application for creating talking head videos. Upload any face photo - a headshot, illustration, historical portrait, or AI-generated image - and turn it into a speaking video in minutes.

Creating Your First Video

  1. Upload a source image

    Choose a photo with a clear, front-facing face. D-ID also provides stock presenter images. Supported formats: JPG, PNG, WebP.

  2. Add your script

    Type text or upload an audio file. For text, select from 100+ voices across 30+ languages.

  3. Customize settings

    Adjust expression intensity, head movement range, and eye contact behavior.

  4. Generate

    Click Generate. Rendering typically takes 30-90 seconds depending on video length.

Source Image Guidelines

RequirementRecommendedAvoid
Face angleFront-facing, slight angles OKProfile or extreme angles
Resolution512x512px minimumBlurry or low-res images
ExpressionNeutral or slight smileOpen mouth, extreme expressions
LightingEven, well-lit faceHeavy shadows, backlighting
OcclusionFull face visibleHands covering face, large accessories

Advanced Features

  • AI-Generated Presenters: Generate unique face images using D-ID's built-in AI image generator
  • Audio Upload: Upload your own voice recording for exact control over delivery
  • Multiple Clips: Chain multiple clips together for longer presentations
Creative Use Cases: D-ID is uniquely powerful for animating non-photographic sources: paintings, illustrations, historical photos, AI art. Museums use it to bring historical figures to life, and educators animate textbook illustrations for engaging content.

Ready to Go Deeper?

Live instructor-led courses from our partners. Affiliate disclosure.