MIDI AI
by AI Mindset
aimindset.org
@ai_mind_set
Hand Control
Text to Music
Controls
Text Input
Tempo
120
BPM
Instrument
Piano
Electric Piano
Strings
Synth Pad
Pluck
Bell
8-Bit
Reverb
30
%
▶ Play
⏹ Stop
Piano Roll
Zoom
Ready — Press Play or Space
0 notes
Camera
Select camera...
LIVE Mode (L)
Synth FX (1)
Loop FX (2)
Focus (B)
Mute (M)
Voice Loop
Audio Input (use BlackHole for system audio)
Select audio source...
Audio
Record (R)
Overdub (T)
Play
Clear
Export
Waveform
Saw
Sine
Square
Triangle
Vol
70
Speed
100
Mapping
Raise →
Pitch
Filter
L.Speed
L.Filter
Tilt →
Filter
Reso
Detune
None
Glide →
Pan
Delay
None
Grasp →
Volume
L.Vol
Filter
None
Camera Feed
Inactive
Raise
—
Tilt
—
Glide
—
Slide
—
Flex
—
Grasp
—
Dimensions of Air
Raise (Y)
Tilt (Angle)
Glide (X)
Slide (Depth)
Flex (Fingers)
Grasp (Pinch)
Output Waveform
Camera inactive — Click "Start Camera"
0 FPS
?
MIDI AI — Hand Gesture Music Controller
Recording & Playback
R (hold)
Record new loop
Hold R key to record your voice. Release to stop. Loop auto-plays after recording.
T (hold)
Overdub layer
Record additional layer on top of existing loop. Same volume as original.
Space
Play / Stop loop
X
Clear loop
E
Export session (WAV)
Modes & FX Toggles
L
LIVE Mode
Real-time voice modulation with hand. Your voice passes through filter controlled by gestures. No synth sound — pure voice processing.
1
Synth FX toggle
When ON, hand gestures affect the synthesizer (pitch, filter, etc.)
2
Loop FX toggle
When ON, hand gestures affect the loop (speed, filter). Enable both for combined control.
B
Focus Mode
Visual effect — blurs and darkens background, keeping only hand in focus.
M
Mute Synth
Mutes the hand-controlled synthesizer sound. Loop playback continues.
System Audio (Spotify, etc.)
To modulate system audio from Spotify/YouTube:
1. Install
BlackHole
(free virtual audio driver)
2. In macOS Audio MIDI Setup → Create Multi-Output Device (BlackHole + Speakers)
3. Set Multi-Output as system output
4. Select "BlackHole" in Audio Input dropdown
5. Enable Live Mode (L) to hear modulated audio
6 Dimensions of Air (Synth Mode)
Raise
Hand Y position
Move hand up/down → Pitch or Filter frequency (configurable)
Tilt
Wrist angle
Rotate wrist → Filter resonance or detune
Glide
Hand X position
Move hand left/right → Stereo pan or delay amount
Slide
Hand depth (size)
Move hand closer/further from camera
Flex
Finger curl
Curl fingers toward palm
Grasp
Pinch gesture
Pinch thumb to index → Volume control
Live Mode Voice Control
Raise
Filter frequency (200-8000 Hz)
Tilt
Filter resonance (Q)
Grasp
Voice volume
Open hand = full volume, pinch = mute
Close (Esc)