Hi,
I'm trying to read spectogram jpgs and convert them back into audio, but I can't work out how to do it. I've tried using pix_data and pix_pix2sig~ but I cant get anything to work.#

at the moment Im reading each column of pixels in the image, but this is incredibly slow, and I ant work out how to convert the resulting list into audio.

Is there a proper way to do this please?

Thanks very much.

How about histograms of the stills, windowed to fit in a [rifft~]?

@sunji

I misread the question. Forget the part about the histogram and just fit the spectrogram in a [rifft~] window.