Audio source
Audio · Required
Loading the current model…
We could not open this model.
Return to the catalogue and choose an available model.
Back to the catalogue
- Mirage
- Standard
- Generate video
Mirage Avatar X
Generate identity-consistent, expressive avatar performances from script or audio.
Compare Mirage Avatar X settings and cost estimates. Audio-driven presenters with the option to guide appearance using either a still image or an existing reference video.
- Avatar
- With audio
Mirage Avatar X pricing example
$2.10 Estimated per run
Estimate checked . This example uses the configuration shown above. Inputs and settings can change the price; check the estimate for your own run before generating. Project storage is billed separately.
How AI usage and project pricing work →Curated output references.
What goes in. What comes back.
The model defines every slot it reads and every result it returns. Required inputs must be present before a run can begin.
Prompts and source material
Image reference
Image · Optional
Video reference
Video · Optional
Files and structured results
Video
Video
Configure the run.
| Control | Available values | Requirement |
|---|
Works especially well for
- Audio-driven presenters with the option to guide appearance using either a still image or an existing reference video.
Know the trade-offs
- This entry requires audio but exposes no script field, resolution selector, or emotion preset. A reference guides identity without guaranteeing every gesture will match.
Continue from the result
Use it inside a production
- Suggested exercise: reuse a short presenter video as the visual reference for a new speech track and inspect face identity, body posture, and background continuity. →
- Choose HeyGen Avatar 4 for explicit size/aspect choices from a photograph; choose Mirage when an existing video is the useful visual reference. →
Compare similar models
Compare models for the same capability. Check their inputs, output settings, and estimate using the same brief.
Configure the model.
Keep the result in the cut.
The generation returns to the scene, asset folder and timeline it belongs to.