Single Second Sound Conversion — Single Second Studios
v1.0
How it works: Each image column maps to one STFT frame. Pixel brightness sets the magnitude of each frequency bin directly. Color: Left channel = Red, Right channel = Blue. Green is recovered as (L+R)×0.5 on decode — a perceptually good approximation since green is highly correlated with luminance.
01 — Input Image
⬡
DROP IMAGE HERE or CLICK TO BROWSE
PNG · JPG · GIF · WEBP — Any size
Source Image
02 — Parameters
FFT Size — 4096
Overlap — 75%
Min Freq — 20 Hz
Max Freq — 20000 Hz
Freq Scale
Sample Rate
Load an image to see encoding info.
STFT · WAV OUTPUT
Load an image to begin.
03 — Output Audio
Decode: Forward FFT per overlapping frame. For each output pixel, the magnitude of its mapped frequency bin is read directly. Identical settings to the encode pass give the best reconstruction. The "Test Decode" button mirrors all settings automatically.