AI duet rap video generator that creates shareable vertical clips from two photos
Convert HTML, CSS and JavaScript animations into MP4 videos locally on Windows
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
CA
Pricing model
Paid
Freemium
Pricing
Pro: $9.9/pack with 300 credits valid for 365 days; Ultimate: $29.9/pack with 1200 credits valid for 365 days; Max: $59.9/pack with 3000 credits valid for 365 days. One-time credit packs with 25% discount available on yearly billing.
Free trial: $0 with 10 renders, up to 1080p, up to 10 seconds per video. Desktop Pro: CAD $19 one-time payment with unlimited conversions, batch rendering, up to 4K resolution, and activation on up to 3 machines.
Key features
Generate lyrics and beat from a text prompt
Render shareable 9:16 vertical video clips
Upload two performer photos for AI face animation
Export stems and MIDI for generated tracks
Train custom voice models on Ultimate and Enterprise plans
Preview first 8 bars free before committing credits
Priority render queue on Pro and Ultimate tiers
Guest checkout option without account creation
Supports HTML, CSS, Canvas and WebGL animations
Local rendering with private file processing
Batch rendering with up to 4 concurrent workers
Hardware GPU encoding (NVIDIA NVENC, AMD AMF, Intel QSV) with CPU fallback
Up to 4K UHD resolution (3840 x 2160)
Audio capture and external audio file support
Activation on up to 3 machines
Automatic browser crash recovery
30-day offline grace period after activation
Open-source MIT Node.js CLI alternative
What makes it different
Renders a mastered rap video in minutes without studio recording
Full commercial ownership of generated content
Encrypted photo uploads with automatic purge capability
AI voice model tuned for rap cadence and flow
Works for diverse use cases from weddings to corporate events to live commerce
All rendering happens locally on your machine
Pre-bundled Chromium and FFmpeg, no terminal or setup required
Test animation rendering for free before purchasing
Deterministic rendering with frame-by-frame control