This website uses cookies to offer optimum functionality. More info

Feature list

Please note: AI-supported recognition is only available in the new version capella audio2score pro 4.

Feature comparison:

Features capella audio2score capella audio2score pro
General    
Development stage and year Version 1 (2021) Version 4 (2023)
For macOS
For Windows 64 Bit
Automatic software updates
Continuous program maintenance
Demo and trial version available
Note by note recognition capella audio2score capella audio2score pro
AI-assisted note recognition  
Distinction of three timbres: 1. winds, 2. strings, 3. piano  
Optimized mode for solo piano  
Recognition can be combined with the recognition of a singing voice  
Suitable for pieces without vocals (stereo suppression of vocals and sole recognition of accompaniment possible, depending on recording)
Recognition of polyphonic sounds of any instrumental recordings (except percussion)
Automatic arrangement of the recognized notes for various ensembles (selectable: piano, string quartet, wind quintet, guitar, monophonic, etc.); independent of the original
Intelligent distribution of notes to voices (no fixed split points, but formation of lines)
Specification of different levels of difficulty for piano arrangements; Level of detail slider
Harmony detection capella audio2score capella audio2score pro
Harmony symbols  
Holistic recognition capella audio2score capella audio2score pro
Suitable for pieces without or with vocals  
Recognition of the melody (instrumental and/or vocal; with differentiation)  
Bass line detection  
Realization of accompanying voices based on the harmonies  
Predefined ensembles selectable (piano, orchestra, band, ...)  
Robust, well playable result even with complex pieces  
Further recognition capella audio2score capella audio2score pro
Recognition of barlines (can be corrected if desired)
Key detection (can be corrected if desired)
Tuning detection (concert pitch a')

Automatic local derivation of enharmonic changes (“F sharp” or “G flat”?) according to the harmonic context

Free configurability: set up any desired ensembles with individual voices, recognition settings, quantization and accompaniment patterns  
Combination of note-by-note and holistic recognition; creation of templates for new projects  
Notes can be transposed if desired
Support of transposing instruments according to templates any
Editing capella audio2score capella audio2score pro
Support from the sound tissue, which provides visual insight into the sound  
Display of tones as tone boxes (piano roll view) and as note images  
Intuitive editing in both views, real-time synchronization  
Post-processing of harmonies (accompanying voices adapt)  
Barlines and beat strokes: changeable by manually setting marks  
Barlines: changeable by tapping along with playback
Adjustable formatting of the notes (page size, bar numbers, ...) partly
Voice editor for the score layout of all voices (clefs, line spacing, solid barlines, etc.)  
Operation capella audio2score capella audio2score pro
All settings with visual and acoustic preview in real time
Qualitative playback of recognized notes via soundfont (capella-tune)
Control listening of the result by simultaneous playback of the original (mixer function), at any tempo (time stretching)
Mouse mode: playback of original and/or recognition by mouse swipe at any tempo  
Voice filtering for tones boxes and playback  
Modern MDI interface in which multiple documents / views can be placed side by side  
Easy-to-use, limited wizard interface for getting started
Switch to the main program (complete features) and back possible at any time  
Direct transfer of the notes to capella
Help notes in the program and detailed documentation
File formats capella audio2score capella audio2score pro
Input (audio): MP3, WAV; WMA (Windows only)
Output (sheet music): CapXML (capella), MusicXML, PDF
Output (MIDI): SMF-0, SMF-1  
This can not be done by the software
No recognition of percussion
No differentiation between individual instruments; only the instrument groups are differentiated according to wind instruments, strings or piano (with harpsichord, guitar). For example, a violin can be distinguished from a clarinet, but not from a cello. The automatic distribution of notes to voices within an instrument group is done according to pitch.
Recognition of the vocals succeeds more or less, depending on the recording
You should specify the time signature manually (positioning of the barlines is done automatically)