another attempt, using svg path for rendering to audio

render.py

@@ -20,49 +20,45 @@
 
 import sys
 import wave
-
-import pyaudio
-from PIL import Image
+from svgpathtools import svg2paths
 
 samplerate = 44100 #192000
 default_duration = 5.0
-
-def read_image(image):
-    print("image: width={} height={} total={}".format(image.width, image.height, image.width * image.height))
-
-    # resize coordinates for conversion to amplitude values
-    max_len = max(image.width, image.height)
-    fact = 32767 / max_len
-    sw, sh = int(image.width * fact), int(image.height * fact)
-    print("amplitude: width={} height={}".format(sw, sh))
+default_outfile = "out.wav"
+
+def read_image(filename):
+    paths, attributes = svg2paths(filename)
+    path = paths[0]
+    if len(paths) > 1:
+        print("WARNING: multiple paths in file. will just draw first one.")
+
+    print("paths={} segments={}".format(len(paths), len(path)))
+
+    points = [[path[0].start.real, path[0].start.imag]]
+    p_min = [points[0][0], points[0][1]]
+    p_max = [points[0][0], points[0][1]]
+    for segment in path:
+        p = [segment.end.real, segment.end.imag]
+        for i in range(0, 2):
+            if p[i] < p_min[i]:
+                p_min[i] = p[i]
+            if p[i] > p_max[i]:
+                p_max[i] = p[i]
+        points.append(p)
+    print("min={} max={}".format(p_min, p_max))
 
     data = bytearray()
-    for x in range(0, image.width):
-        for y in range(0, image.height):
-            if image.getpixel((x, y))[3] > 127:
-                xc, yc = int((x - (image.width / 2)) * fact), int((y - (image.height / 2)) * fact)
-                data.extend(yc.to_bytes(2, byteorder="little", signed=True))
-                data.extend(xc.to_bytes(2, byteorder="little", signed=True))
+    for n in range(0, len(points)):
+        for i in range(0, 2):
+            v = points[n][i]
+            v -= p_min[i]
+            v /= p_max[i] - p_min[i]
+            c = int((v * 2 - 1) * (32767 / 100 * 70))
+            data.extend(c.to_bytes(2, byteorder="little", signed=True))
     return data
 
-def play_waveform(data):
-    pa = pyaudio.PyAudio()
-
-    # int16
-    stream = pa.open(format=pa.get_format_from_width(2),
-                    channels=2,
-                    rate=samplerate,
-                    output=True)
-
-    stream.write(data, int(len(data) / 4), True)
-
-    stream.stop_stream()
-    stream.close()
-
-    pa.terminate()
-
-def write_waveform(data):
-    with wave.open("out.wav", "w") as f:
+def write_waveform(data, filename):
+    with wave.open(filename, "w") as f:
         f.setnchannels(2)
         f.setsampwidth(2)
         f.setframerate(samplerate)
@@ -71,16 +67,20 @@ def write_waveform(data):
 def main():
     if len(sys.argv) <= 1:
         print("Usage:")
-        print("\t" + sys.argv[0] + " image.png [seconds]")
+        print("\t" + sys.argv[0] + " image.png [out.wav] [seconds]")
         sys.exit(1)
 
-    if len(sys.argv) >= 3:
+    if len(sys.argv) == 3:
+        duration = float(sys.argv[2])
+        outfile = default_outfile
+    if len(sys.argv) >= 4:
         duration = float(sys.argv[2])
+        outfile = sys.argv[3]
     else:
         duration = default_duration
+        outfile = default_outfile
 
-    with Image.open(sys.argv[1]) as image:
-        wave = read_image(image)
+    wave = read_image(sys.argv[1])
 
     samplecount = int(len(wave) / 2 / 2) # stereo, int16
     drawrate = samplerate / samplecount
@@ -92,8 +92,7 @@ def main():
         data.extend(wave)
     print("len={}".format(len(data)))
 
-    #play_waveform(bytes(data))
-    write_waveform(bytes(data))
+    write_waveform(bytes(data), outfile)
 
 if __name__ == "__main__":
     main()

toolbox.svg

@@ -0,0 +1,48 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   width="18.108976mm"
+   height="21.025101mm"
+   viewBox="0 0 18.108976 21.025101"
+   version="1.1"
+   id="svg1"
+   inkscape:version="1.3.2 (091e20ef0f, 2023-11-25, custom)"
+   sodipodi:docname="toolbox.svg"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg">
+  <sodipodi:namedview
+     id="namedview1"
+     pagecolor="#505050"
+     bordercolor="#eeeeee"
+     borderopacity="1"
+     inkscape:showpageshadow="0"
+     inkscape:pageopacity="0"
+     inkscape:pagecheckerboard="0"
+     inkscape:deskcolor="#d1d1d1"
+     inkscape:document-units="mm"
+     inkscape:zoom="9.7401438"
+     inkscape:cx="34.291075"
+     inkscape:cy="39.732473"
+     inkscape:window-width="1920"
+     inkscape:window-height="1020"
+     inkscape:window-x="0"
+     inkscape:window-y="420"
+     inkscape:window-maximized="1"
+     inkscape:current-layer="layer1" />
+  <defs
+     id="defs1" />
+  <g
+     inkscape:label="Layer 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(-45.755199,-45.487921)">
+    <path
+       inkscape:connector-curvature="0"
+       id="path32"
+       style="fill:none;fill-opacity:1;fill-rule:nonzero;stroke:#000000;stroke-width:0.0352778;stroke-opacity:1"
+       d="m 54.809672,66.488838 -0.0032,-0.0019 -0.0033,0.0019 -0.0032,-0.0057 -9.011829,-5.198633 h -0.0153 l 0.0029,-10.567212 9.035378,-5.20901 9.028924,5.208587 v 4.160979 h -0.01739 l 0.01739,0.03006 -1.862843,1.074597 1.862843,1.074702 -5.64e-4,9.88e-4 5.64e-4,2.82e-4 v 4.202042 h -0.0088 l 0.0088,0.01517 -9.027266,5.207453 -0.0032,0.0057 m 0.897926,-11.088264 v 0 l 0.01475,8.37463 6.246777,-3.580133 v -2.057153 l -1.864043,-1.075267 -1.899073,1.095516 V 55.99825 l 3.763116,-2.170818 v -2.029848 l -7.160824,-4.130957 -7.164416,4.133003 v 8.395441 l 6.19276,3.569109 v -7.281566 l -1.492427,0.863212 -1.871098,-1.079429 5.594315,-3.236454 1.871909,1.079994 -2.231742,1.290637" />
+  </g>
+</svg>