audio info

__init__.py

@@ -87,6 +87,7 @@ from .nodes.audio.audio_nodes_utility import (
     AudioSubtract,
     AudioConcatenate,
     AudioDither,
+    AudioInfo,
 )
 
 from .nodes.flex.feature_extractors import(
@@ -372,6 +373,7 @@ NODE_CLASS_MAPPINGS = {
     "AudioPitchShift":              AudioPitchShift,
     "AudioTimeStretch":             AudioTimeStretch,
     "AudioDither":                  AudioDither,
+    "AudioInfo":                    AudioInfo,
     "AudioGain":                    AudioGain,
     "AudioFade":                   AudioFade,
     "AudioPad":                     AudioPad,

nodes/audio/audio_nodes_utility.py

@@ -189,6 +189,46 @@ class AudioSubtract(AudioUtility):
         subtracted_waveform = waveform1 - waveform2
         return ({"waveform": subtracted_waveform, "sample_rate": sample_rate},)
 
+class AudioInfo(AudioUtility):
+    @classmethod
+    def INPUT_TYPES(cls):
+        return {
+            "required": {
+                "audio": ("AUDIO",),
+            }
+        }
+
+    RETURN_TYPES = ("FLOAT", "INT", "INT", "INT", "FLOAT", "FLOAT", "FLOAT", "STRING")
+    RETURN_NAMES = ("duration_seconds", "sample_rate", "num_channels", "num_samples", 
+                   "max_amplitude", "mean_amplitude", "rms_amplitude", "bit_depth")
+    FUNCTION = "get_audio_info"
+
+    def get_audio_info(self, audio):
+        waveform, sample_rate = audio['waveform'], audio['sample_rate']
+        
+        # Calculate basic properties
+        num_channels = waveform.shape[1]
+        num_samples = waveform.shape[2]
+        duration_seconds = num_samples / sample_rate
+        
+        # Calculate amplitude statistics
+        max_amplitude = float(torch.max(torch.abs(waveform)))
+        mean_amplitude = float(torch.mean(torch.abs(waveform)))
+        rms_amplitude = float(torch.sqrt(torch.mean(waveform ** 2)))
+        
+        # Get bit depth from dtype
+        bit_depth = str(waveform.dtype)
+        
+        return (
+            duration_seconds,
+            sample_rate,
+            num_channels,
+            num_samples,
+            max_amplitude,
+            mean_amplitude,
+            rms_amplitude,
+            bit_depth
+        )
 
 class AudioDither(AudioUtility):
     @classmethod

pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "comfyui_ryanonyheinside"
 description = "Custom nodes introducing particle simulations, optical flow, audio manipulation & reactivity, and temporal masks"
-version = "1.11.0"
+version = "1.12.0"
 license = {file = "LICENSE"}
 dependencies = ["pygame","opencv-python==4.10.0","scipy","torchaudio", "pillow","librosa==0.10.2","pymunk==6.8.1","matplotlib","openunmix","mido"]
 

readme.md

@@ -40,6 +40,8 @@
 
 <details>
 <summary><h3>🆕 Recent Updates:</h3></summary>
+
+- 11/19/24 - **AudioInfo**: Added a node that returns audio information, including duration, sample rate, number of channels, number of samples, max amplitude, mean amplitude, and RMS amplitude.
 - 11/8/24 - **DOOM**: Will it run DOOM? Yes. Yes it will.
 - 11/6/24 - **Some cleanup in prep for v2**: Control CogVideo by converting features to spline data
 - 11/1/24 - **Feature to Spline Data**: Control CogVideo by convert features to spline data