Free: First 1K conversion with 2 layers. Starter: $9.9/month with 1,200 credits per month. Pro: $19.9/month with 2,500 credits per month. Pay per layer: 5 credits at 1K, 8 credits at 1.5K, 10 credits at 2K.
Key features
Transcribe audio and video from files or URLs
100+ language support
Speaker detection and diarization
Automatic timestamps
Transcript translation
Browser extension for tab audio capture
Multiple export formats
Transcript editing and proofing
Chat with transcript
AI proofreading and formatting
Automatic layer separation of text, subjects, graphics and background
Rebuilt background with filled gaps
Support for PNG and JPEG input formats up to 10MB
Adjustable layer count from 2 to 9 layers or Auto
Small element enlargement for sharp text in outputs
Output size options: 1K, 1.5K, and 2K resolution
Layer preview and toggle functionality
Character-accurate text recognition in layers
What makes it different
Free without signup required
Browser extension for direct tab transcription
Privacy-first approach with local processing for guests
Support for 100+ languages with speaker detection
Strict transcription guardrails to reduce AI hallucination
Converts flat images into fully editable layers without manual masking or pen tool work
Intelligently rebuilds backgrounds with filled gaps where elements were removed
Exports complete layer stacks as PSD with position and order already preserved
Faster alternative to Photoshop's manual layer separation process
VocaScript
IntoLayers