Turn Any Audio Into MIDI
AI-powered audio transcription. Turn audio into editable, multi-track MIDI. Preview your transcription for free. Download it for $1 per minute.
Transcription Features
Multi-Track Instrument Detection
The model can recognize over 100 MIDI program instruments. These instruments are merged into 27 instrument categories.
Show Instrument Groups Hide Instrument Groups
MIDI program · Instrument
Piano
- 000 Acoustic grand piano
- 001 Bright acoustic piano
- 002 Electric grand piano
- 003 Honky tonk piano
Electric Piano
- 004 Electric piano 1
- 005 Electric piano 2
Plucked keys
- 006 Harpsicord
- 007 Clavinet
Keyboard percussion
- 008 Celesta
- 009 Glockenspiel
- 010 Music box
- 011 Vibraphone
- 012 Marimba
- 013 Xylophone
- 014 Tubular bell
Organ
- 016 Hammond / drawbar organ
- 017 Percussive organ
- 018 Rock organ
- 019 Church organ
- 020 Reed organ
Accordion
- 021 Accordion
- 023 Tango accordion
Harmonica
- 022 Harmonica
Acoustic guitar
- 024 Nylon string acoustic guitar
- 025 Steel string acoustic guitar
Electric guitar - clean
- 026 Jazz electric guitar
- 027 Clean electric guitar
- 028 Muted electric guitar
Electric guitar - distorted
- 029 Overdriven guitar
- 030 Distortion guitar
- 031 Guitar harmonics
Bass
- 032 Acoustic bass
- 033 Fingered electric bass
- 034 Picked electric bass
- 035 Fretless bass
- 036 Slap bass 1
- 037 Slap bass 2
Synth bass
- 038 Synth bass 1
- 039 Synth bass 2
Strings
- 040 Violin
- 041 Viola
- 042 Cello
- 043 Contrabass
- 044 Tremolo strings
- 045 Pizzicato strings
- 046 Orchestral strings / harp
- 047 Timpani
- 048 String ensemble 1
- 049 String ensemble 2 / slow strings
- 110 Fiddle
Synth strings
- 050 Synth strings 1
- 051 Synth strings 2
Vocals
- 052 Choir aahs
- 053 Voice oohs
- 054 Synth choir / voice
Horns
- 056 Trumpet
- 057 Trombone
- 058 Tuba
- 059 Muted trumpet
- 060 French horn
- 061 Brass ensemble
Synth brass
- 062 Synth brass 1
- 063 Synth brass 2
Saxophone
- 064 Soprano sax
- 065 Alto sax
- 066 Tenor sax
- 067 Baritone sax
Reed
- 068 Oboe
- 069 English horn
- 070 Bassoon
- 071 Clarinet
- 111 Shanai
Flute
- 072 Piccolo
- 073 Flute
- 074 Recorder
Folk winds
- 075 Pan flute
- 076 Bottle blow / blown bottle
- 077 Shakuhachi
- 078 Whistle
- 079 Ocarina
Synth lead
- 080 Synth square wave
- 081 Synth saw wave
- 082 Synth calliope
- 083 Synth chiff
- 084 Synth charang
- 085 Synth voice
- 086 Synth fifths saw
- 087 Synth brass and lead
Synth pad
- 088 Fantasia / new age
- 089 Warm pad
- 090 Polysynth
- 091 Space vox / choir
- 092 Bowed glass
- 093 Metal pad
- 094 Halo pad
- 095 Sweep pad
- 096 Ice rain
- 097 Soundtrack
- 098 Crystal
- 099 Atmosphere
- 100 Brightness
- 101 Goblins
- 102 Echo drops / echoes
- 103 Sci fi
Ethnic
- 015 Dulcimer
- 104 Sitar
- 105 Banjo
- 106 Shamisen
- 107 Koto
- 108 Kalimba
- 109 Bag pipe
Percussion
- 055 Orchestra hit
- 112 Tinkle bell
- 113 Agogo
- 114 Steel drums
- 115 Woodblock
- 116 Taiko drum
- 117 Melodic tom
- 118 Synth drum
- 119 Reverse cymbal
SFX
Not included- 120 Guitar fret noise
- 121 Breath noise
- 122 Seashore
- 123 Bird tweet
- 124 Telephone ring
- 125 Helicopter
- 126 Applause
- 127 Gunshot
Drums
- 128 Drums
General MIDI Drum Transcription
47 different drum and percussion pieces that follow the General MIDI drum mapping(plus some commonly used extensions)
Show Drum List Hide Drum List
MIDI note · Drum / percussion
Note Velocity
Feeling and groove aren't just about what notes are played, but how they're played.
Instrument Suppression
If necessary, you can tell the model not to output unwanted instruments.
Audio Preview
Hear an audio rendering of the MIDI transcription, and only pay if you're happy.
Simple Process
How It Works
Three steps from audio to MIDI. No subscriptions, no hidden fees.
1. Upload Audio
Drag and drop any audio file — MP3, WAV, OGG, FLAC, or M4A. Up to 50MB.
2. Preview Result
See an interactive piano roll preview and listen to the MIDI playback before committing.
3. Download MIDI
Accept the result and download your MIDI file instantly. Only pay if you're happy.
Hear The Difference
Industry-Leading Accuracy
No audio to midi converter is perfect, so here are some demo tracks so you can get a feel for where our model performs well, and where it doesn't
Press play for an automatic Original-to-MidifyAI comparison, or take control of the crossfade yourself.
At the Gates of Heaven
Nonak
Pop
Acoustic
Rock
Laid Back
Hopeful
Drag to blend, or choose a source below.
Chromatic Soul
MudiG
Electronic
Soul
Ambient
Upbeat
Drag to blend, or choose a source below.
Drum Breaks
Unknown
Drums
Breaks
Drag to blend, or choose a source below.
Folk Circuit
Nonak
Pop
Acoustic
Hopeful
Sentimental
Drag to blend, or choose a source below.
Impatient
Sascha Ende
Cinematic
Ambient
Drag to blend, or choose a source below.
In The Quiet After You
Off Beat
Pop
Laid Back
Sentimental
Melancholic
Drag to blend, or choose a source below.
No Words
müxa
Pop
Lofi
Hip Hop
Dramatic
Dark
Drag to blend, or choose a source below.
Not In My Store
Off Beat
Pop
Happy
Groovy
Drag to blend, or choose a source below.
Orderly Chaos
Off Beat
Classical
Cinematic
Dramatic
Hopeful
Drag to blend, or choose a source below.
Sample Smörgåsbord I
Various
Electronic
Samples
Drag to blend, or choose a source below.
The Chosen One
Off Beat
Cinematic
Dramatic
Hopeful
Drag to blend, or choose a source below.
With The Winds
VOLO
Electronic
Uplifting
Atmospheric
Hopeful
Drag to blend, or choose a source below.
Wun Dak
Off Beat
Electronic
Happy
Hopeful
Upbeat
Drag to blend, or choose a source below.
Pricing
Simple, Pay-Per-Use Pricing
No subscriptions. No commitments. Only pay for what you use.
Pay Per Transcription
$1 / minute
- Preview before you pay
- No subscription required
- Instant MIDI download
- Audio playback preview
- Supports MP3, WAV, OGG, FLAC, M4A
Audio is rounded up to the nearest minute
Frequently asked questions
-
Yes. We think it's the best audio to MIDI converter out there, but of course we would say that.
But you don't have to take our word for it, we have a number of demo tracks you can listen to. We deliberately chose challenging tracks to show where the model does well, but also where it struggles. We chose tracks with dense instrumentation, fast notes, wide dynamic range variation, and post-processing FX. These demo tracks have not been adjusted or altered to remove any flaws. We took the output MIDI, picked some VST instruments that were roughly similar to the original track, did some very basic mixing, and then output the result to audio.
Since the audio is transcribed by AI, it's impossible for us to say how well it will perform on any given audio file, so that's why we let you hear the result before you decide if it's worth spending money on. Our goal is not to trick you, we only want you to pay if you're happy with the transcription results. If our model doesn't do as well as you had hoped it would, it won't cost you a penny, but we hope you'll try us again in the future if you have another audio file you want converted to MIDI.
-
MidifyAI uses AI/Machine Learning. This means it's a mathematical model that learns to convert the numbers of a digial audio waveform, into different numbers that represent MIDI events.
It works in a very similar way to machine translation, like Google Translate. Except instead of translating English into Spanish, it translates digital audio into MIDI. It learns the patterns in the "language" by looking at lots and lots of examples, and then tries to identify similar patterns in whatever audio you give it as input.
-
We don’t use your uploads to train our AI. We temporarily store your source audio on our servers while it is being transcribed. We automatically delete your source audio after processing ends, whether it succeeds or fails. MIDI files and generated audio previews are kept separately so you can review and download your results.
Even if you wanted to allow us to train on your audio, we would have to politely decline, as it would be of no use to us. Training a music transcription model requires audio and a precisely aligned transcription.
So where does the data come from? Other than one publicly available dataset of vocal transcriptions, we generate every second of our training data in-house. We have a collection of over 2,500 digital instruments, as well as over 10,000 drum samples that we use to generate our data. Yes, we've listened to every single instrument and every single drum sample, and yes it's as tedious and boring as it sounds.
-
If you're not happy with the results, then you don't pay anything.
We believe that our model can transcribe your audio better than any other tool out there. If we're wrong about that, then it should come out of our pocket, not yours.
-
The model takes roughly ⅓ the length of the audio. So a 5 minute audio clip would take between 1½ and 2 minutes. Clips with less dense notes and drums will be a bit faster.