On the Hailuo AI App: free tier and paid monthly plans (rates listed in app). On MiniMax Open Platform: billed per output second, with 2K tier priced above 768p tier. On this site: 18 credits per second at 768p and 29 credits per second at 2K, with annual plans showing 50% discount and various month
Key features
Removes background noise from audio and video files
Built-in noise-free recorder for direct recording
Echo and reverb reduction
Automatic volume adjustment
Support for multiple audio and video formats
Music removal and vocal isolation tools
Real-time speech enhancement using DeepFilterNet
Secure file processing with no storage on servers
Simple and intuitive user interface
Multimodal reference input: images, video, and audio
Context-IR token-based pricing variant
Downloadable weights for local deployment
H3-Contextual Omni Representation for modality bridging
Up to 12 reference files with caption compression
What makes it different
AI learns what human speech looks like and removes everything else while keeping voice natural
Processes audio and video files directly without separate extraction step
Uses DeepFilterNet for real-time speech enhancement without robotic artifacts
Completely free to try with no signup required
Handles complex, non-stationary background noise like wind and traffic
Only model generating video and audio together natively
2K output at lower per-second rate than competitors
Downloadable open weights available
Accepts richer multimodal reference input than competitors
Noise Reducer AI
MiniMax H3