On-device pose estimation SDK for fitness and rehab apps
Upload a selfie, get five celebrity matches from 350 public figures
Stage
Not given
Not given
Founded
2023
Not given
Based in
FR
Not given
Pricing model
Freemium
Free
Pricing
Free tier: €0, up to 200 tracking API calls monthly, 100 AI credits/month, non-commercial use only. Developer: €50/month, up to 1000 tracking API calls monthly, 500 AI credits/month, commercial use. Business Plan: from €150/month with custom API call limits, custom AI credits, and dedicated support.
Not given
Key features
Free on-device keypoints with 17 COCO points requiring no API key
Rep counting for exercises like squats and push-ups
Joint angle calculations
Form score feedback
Cross-platform: React Native, iOS, Android and web
On-device processing with no video upload
Works offline
WebView and iframe integration option
Ready-to-use built-in motion tracking tools
AI assistant for snippet generation
Compares uploaded photo with 350 public figures
Returns five ranked celebrity matches
Face detection and alignment using OpenCV YuNet
Feature vector comparison using cosine similarity
Photos processed in memory, never saved or used for training
Generates shareable downloadable card with match
No account creation required
Supports JPG, PNG, and WebP formats up to 8 MB
Browses 928 licensed reference photos from Wikimedia Commons
Combines multiple reference photos per celebrity into single prototype
What makes it different
Gives fitness and rehab apps vision to analyze actual movement instead of assuming users followed along
Free keypoints tier allows testing and experimentation before paying for analysis features
Single integration works across React Native, iOS, Android and web platforms
Fast real-time performance: 51 FPS on iPhone 12 and 34 FPS on Pixel 5
No photo storage or training reuse of uploaded images
Transparent methodology with published accuracy limitations and test evidence
Based on real feature comparison, not random results or made-up percentages
Licensed celebrity library with attribution and Wikimedia Commons sources