Remove text, captions and hardcoded subtitles from videos with AI background reconstruction
The unified AI music generation API for developers
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Not given
Freemium
Pricing
Free: 30 free seconds per month for eligible accounts (sign-in required, no credit card needed). Starter subscription: $24.90/month for 600 seconds (10 minutes). Pro subscription: $74.90/month for 2,000 seconds (33 minutes 20 seconds). Monthly billing available; yearly billing offers 2 months free.
Free tier with 10 requests per minute. Paid plans: Basic $10/month (1,000 credits), Pro $20/month (2,000 credits), Max $50/month (5,000 credits), Enterprise (custom plans). Yearly plans save 20%. Pay-as-you-go credits available with no expiration.
Key features
Select Area mode for removing specific words, logos, dates or fixed text
Subtitles mode for detecting and removing subtitle lines across video frames
All Text mode for automatically removing detected text across entire videos
Frame-by-frame text detection and removal
Natural background reconstruction without blur
Preserves original video resolution
Supports MP4 and MOV formats up to 60 seconds and 500 MB
Works on hardcoded subtitles and burned-in captions
No watermark on processed videos
Auto-deletion of videos after 7 days
Multi-model access with Stable Audio and MusicGen
Full audio control over genre, mood, tempo, duration and instruments
Fast generation in 30-120 seconds
Global edge network for low latency
Async webhooks for long compositions
Real-time usage analytics dashboard
SOC 2 compliant enterprise security
Multiple audio format support
Lyrics generation with vocals
Track continuation and extension
What makes it different
AI reconstructs background instead of blurring, maintaining original resolution
Three specialized removal modes for different text types
Pay-per-second pricing with no mandatory subscription
Free monthly allowance for eligible accounts without credit card
Single unified API for multiple AI music models instead of separate integrations