Micro-expressions
Laughs like you laugh
Avatar X
Positive: Laughs, then resumes the video
Competitor
Negative: Keeps mouthing "words" through the laugh
Your digital twin that actually looks and sounds like you.
Now you can create more content, reach more people, and show up consistently with your AI twin. Powered by Mirage Avatar X, our most advanced model yet.
Expressive, just like you
While other avatar models struggle to capture human emotions, Avatar X preserves your full range of expressions that make you unmistakably you.
Non-verbal emotion
Reads the silence
Avatar X
Positive: Natural pause with living micro-motion
Competitor
Negative: Dead-eyed idle loop
Quality under pressure
No degradation mid-take
Avatar X
Positive: Same fidelity at 0:59 as 0:01
Competitor
Negative: Mouth shapes degrade; lips stop matching audio
Create anywhere, anytime, for any platform.
Your twin shows up whenever you need it—whether you're creating for social media, presentations, or anywhere in between. Generate in both vertical and horizontal formats without resizing, reshooting, or recording twice.
10 seconds is all you need.
The shortest video input of any avatar platform with the strongest identity preservation. Creating twins from videos creates stronger fidelity than images alone.
Your recording
Mirage Avatar X only needs 10 seconds of footage to make your twin.
Your twin
Your AI twin shares your full identity, voice and mannerisms.
10 seconds of footage
15 seconds of footage
1-5 minutes of footage
Mirage Avatar X vs. previous Mirage models
Avatar X sets a new standard for AI avatars, preserving identity and generating expression with remarkable realism. Same 10-second recording, same script, much better results.
Avatar X
-10-second video reference
-Holds likeness across the full video
-Consistent quality from first frame to last
-Full emotional range
-Natural blinks, glances, and subtle motion
-Learns from your reference footage
Previous model
-Single photo reference
-Drifts from the source photo
-Degrades as the video progresses
-Limited, flatter delivery
-Micro-expressions not supported
-Inferred, often generic
How to make a digital twin in Captions
Record yourself
Record a short video, reading the provided script. You can do this in the Captions app or online.
Add a script
Enter the script you want your twin to deliver.
Create the video
Generate new videos in minutes, and export directly to top platforms.
Frequently asked questions
What do I actually need to record?
One continuous 10-second clip, filmed directly in Captions. Avatar X extracts your expression range, voice character, and motion from that single take. You can optionally add a few reference photos to sharpen quality.
What should I say in my recording?
We give you a short script designed to capture your natural expression range. Just read it the way you'd talk to a friend.
Do I need to add extra photos?
No, Captions creates your twin from the clip alone. You can add other photos if you want to, but it's not necessary.
Is my twin only mine?
Yes. Twins are consent-first. You have to agree that you have consent and the right to make a twin before you create it.
How is this different from other avatar models?
Most platforms need minutes of footage, and their avatars break on anything non-verbal like laughing, pausing, or reacting. Mirage Avatar X builds a fully expressive twin from 10 seconds, and holds frame-accurate lip-sync.
Does my twin sound like me too?
Yes. Our Mirage Audio model builds a voice clone directly from your 10-second video. It captures your inflection, tone, and delivery too.
Do I need to re-record to change how my twin looks?
No. Your 10-second clip is a one-time setup. After that, you can create a Look from a prompt or photo with no camera required.
What video formats are supported?
Horizontal and vertical, so the same twin works for YouTube, ads, Reels, TikTok, and Shorts. You can make videos up to 3 minutes long.
What languages are supported?
Your twin can speak 30+ languages thanks to AI dubbing and translation. You can also add captions or subtitles in 100+ languages.
How are Captions twins different from HeyGen or Synthesia twins?
Most platforms need minutes of footage, and their avatars break on anything non-verbal like laughing or pausing. Avatar X builds a fully expressive twin from 10 seconds of footage and maintains top-notch quality across your entire video.
*From each platform's published requirements.