AI video generation with synced audio from reference images and text prompts
AI music transcription: convert audio to MIDI and sheet music, scan scores, detect song keys
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Paid
Freemium
Pricing
Not given
Free: 5 transcription jobs daily. Downloads are one-time purchases: up to 2 pages $2.99, 3–9 pages $5.99, 10+ pages $9.99 for MusicXML + MIDI; Rehearsal Pack with practice MP3s and slow mixes $3 more. Credit packs: $9 unlocks 4 pieces, $19 unlocks 10. Practice Passes: $9.99 for 30 days or $29 for 90
Key features
Up to 9 reference images per generation
Up to 3 audio references per generation
5 fixed video lengths from 5.875 to 14.375 seconds
4 aspect ratios (16:9, 1:1, 9:16, 4:3)
24 fps frame rate
Real-time rendering for first 3 reference images
First and last frame control
MP4 output saved for 7 days
Text prompt with reference naming
Automatic credit refund for failed generations
Transcribe audio files (MP3, WAV, FLAC, OGG) to MIDI and sheet music
Scan sheet music PDFs and photos into editable MusicXML
Detect song key, Camelot code and BPM
Browser preview with highlighted notes before downloading
Note-matching exercises with microphone or keyboard input
Harmonic-ghost filter to remove phantom octave notes from transcription
Quality metrics displayed on every transcription job
What makes it different
Synced audio and video in a single generation pass
8-step distilled model for fast generation in browser
No installation or GPU required
Tuned transcription engine with harmonic-ghost filter, not an API wrapper
Honest quality metrics on every job showing notes detected and ghosts filtered
Free daily use with no account required
One-time payments per piece, no subscription required
Professional notation engraving and MusicXML output for editing in music software
FastH3 Omni
MelodyWiz