AI-powered image upscaler that reconstructs detail and restores clarity using Real-ESRGAN technology
AI voice cloning and text to speech for voiceovers
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Freemium
Pricing
Not given
Free plan with limited characters. Starter: $1.99/mo with 80,000 audio credits per month. Plus: $5.99/mo with 380,000 audio credits per month. Pro: $9.99/mo with 880,000 audio credits per month.
Key features
Portrait and facial detail reconstruction
Real-ESRGAN-based restoration for degraded images
Support for JPG, PNG, and WEBP formats
Batch processing up to 100 images on Max plan
API access on Max plan
No watermark on paid plans
Commercial license on Max plan
Privacy-first processing
Voice cloning from 5-10 second audio samples
Support for 10 languages including Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish and Italian
Multi-character dialogue with automatic role detection
Up to 2,000 characters per request in free plan, up to 20,000 in Pro
Audio transcription with timestamps and subtitle download
Creator character library with preview and favorites
Emotion and tone control per segment
API access in Plus and Pro plans
What makes it different
Real-ESRGAN-based restoration reconstructs detail rather than interpolating pixels
Specialized modes for different image types deliver optimized results
No signup required to try with free credits
Preserves natural texture and avoids harsh oversharpening artifacts
Works in-browser across desktop and mobile devices
High-fidelity voice replication from just 5-10 seconds of audio
One-click multi-character story audio generation with automatic role detection
Complete workflow from character creation to finished dubbing