Update app.py

app.py

@@ -20,6 +20,7 @@ from faster_whisper import WhisperModel
 from TTS.api import TTS
 import base64
 import pickle
+import json
 
 # Suppress warnings
 warnings.filterwarnings("ignore")
@@ -136,7 +137,8 @@ def auto_eq(audio, genre="Pop"):
         "Acoustic": [(100, 300, -3), (4000, 8000, +2)],
         "Metal": [(100, 500, -4), (2000, 5000, +6), (7000, 12000, -3)],
         "Trap": [(80, 120, +6), (3000, 6000, -4)],
-        "LoFi": [(20, 200, +3), (1000, 3000, -2)]
+        "LoFi": [(20, 200, +3), (1000, 3000, -2)],
+        "Default": []
     }
 
     from scipy.signal import butter, sosfilt
@@ -245,7 +247,7 @@ def process_audio(audio_file, selected_effects, isolate_vocals, preset_name, exp
         status = f"❌ Error: {str(e)}"
         return None, None, status, "", status
 
-# === Visualize Waveform ===
+# === Waveform + Spectrogram Generator ===
 def show_waveform(audio_file):
     try:
         audio = AudioSegment.from_file(audio_file)
@@ -308,17 +310,14 @@ def get_preset_cards():
     return card_paths
 
 # === Load Preset by Name === 
-def load_preset_by_card(name_index):
-    name = preset_names[name_index]
+def load_preset_by_card(evt: gr.SelectData):
+    index = evt.index % len(preset_names)
+    name = preset_names[index]
     return name, preset_choices[name]
 
 # === Logo Embedding (Base64 or file) ===
 def get_logo():
-    try:
-        with open("logo.png", "rb") as img_file:
-            return "data:image/png;base64," + base64.b64encode(img_file.read()).decode()
-    except FileNotFoundError:
-        return "https://via.placeholder.com/400x100?text=AI+Audio+Studio"
+    return "https://via.placeholder.com/400x100?text=AI+Audio+Studio"
 
 # === Main UI === 
 with gr.Blocks(title="AI Audio Studio", css="style.css") as demo:
@@ -329,8 +328,7 @@ with gr.Blocks(title="AI Audio Studio", css="style.css") as demo:
         with gr.Row():
             with gr.Column(min_width=300):
                 input_audio = gr.Audio(label="Upload Audio", type="filepath")
-                effect_checkbox = gr.CheckboxGroup(choices=preset_choices.get("Default", []),
-                                                   label="Apply Effects in Order")
+                effect_checkbox = gr.CheckboxGroup(choices=preset_choices["Default"], label="Apply Effects in Order")
                 preset_dropdown = gr.Dropdown(choices=preset_names, label="Select Preset", value=preset_names[0])
                 export_format = gr.Dropdown(choices=["MP3", "WAV"], label="Export Format", value="MP3")
                 isolate_vocals = gr.Checkbox(label="Isolate Vocals After Effects")
@@ -338,12 +336,15 @@ with gr.Blocks(title="AI Audio Studio", css="style.css") as demo:
             with gr.Column(min_width=300):
                 output_audio = gr.Audio(label="Processed Audio", type="filepath")
                 waveform_img = gr.Image(label="Waveform Preview")
-                genre_out = gr.Textbox(label="Detected Genre")
+                session_log_out = gr.Textbox(label="Session Log", lines=5)
+                genre_out = gr.Textbox(label="Detected Genre", lines=1)
                 status_box = gr.Textbox(label="Status", value="✅ Ready", lines=1)
 
         submit_btn.click(fn=process_audio, inputs=[
             input_audio, effect_checkbox, isolate_vocals, preset_dropdown, export_format
-        ], outputs=[output_audio, waveform_img, _, genre_out, status_box])
+        ], outputs=[
+            output_audio, waveform_img, session_log_out, genre_out, status_box
+        ])
 
     # --- AI Mastering Chain Tab ===
     with gr.Tab("🎧 AI Mastering Chain"):
@@ -384,22 +385,16 @@ with gr.Blocks(title="AI Audio Studio", css="style.css") as demo:
             ("https://via.placeholder.com/150x100?text=Rock", "Rock"),
             ("https://via.placeholder.com/150x100?text=Hip-Hop", "Hip-Hop"),
             ("https://via.placeholder.com/150x100?text=Acoustic", "Acoustic"),
-            ("https://via.placeholder.com/150x100?text=Tube+Saturation", "Tube"),
+            ("https://via.placeholder.com/150x100?text=Tube", "Tube"),
             ("https://via.placeholder.com/150x100?text=Stage+Mode", "Stage Mode"),
             ("https://via.placeholder.com/150x100?text=Vocal+Distortion", "Vocal Distortion")
         ]
 
         preset_gallery = gr.Gallery(value=preset_images, label="Preset Cards", columns=4, height="auto")
         preset_name_out = gr.Dropdown(choices=preset_names, label="Selected Preset")
-        preset_effects_out = gr.CheckboxGroup(choices=[e for e in preset_choices["Default"]], label="Effects")
-
-        def select_preset(evt: gr.SelectData):
-            selected = evt.index
-            name = preset_names[selected % len(preset_names)]
-            effects = preset_choices.get(name, [])
-            return name, effects
+        preset_effects_out = gr.CheckboxGroup(choices=list(preset_choices.keys())[0:], label="Effects")
 
-        preset_gallery.select(fn=select_preset, inputs=[], outputs=[preset_name_out, preset_effects_out])
+        preset_gallery.select(fn=load_preset_by_card, inputs=[], outputs=[preset_name_out, preset_effects_out])
 
     # --- Vocal Doubler / Harmonizer === 
     with gr.Tab("🎧 Vocal Doubler / Harmonizer"):
@@ -408,8 +403,7 @@ with gr.Blocks(title="AI Audio Studio", css="style.css") as demo:
             inputs=gr.Audio(label="Upload Vocal Clip", type="filepath"),
             outputs=gr.Audio(label="Doubled Output", type="filepath"),
             title="Add Vocal Doubling / Harmony",
-            description="Enhance vocals with doubling or harmony",
-            allow_flagging="never"
+            description="Enhance vocals with doubling or harmony"
         )
 
     # --- Remix Mode ---
@@ -435,7 +429,7 @@ with gr.Blocks(title="AI Audio Studio", css="style.css") as demo:
             fn=batch_process_audio,
             inputs=[
                 gr.File(label="Upload Multiple Files", file_count="multiple"),
-                gr.CheckboxGroup(choices=preset_choices.get("Default", []), label="Apply Effects in Order"),
+                gr.CheckboxGroup(choices=list(preset_choices["Default"]), label="Apply Effects in Order"),
                 gr.Checkbox(label="Isolate Vocals After Effects"),
                 gr.Dropdown(choices=preset_names, label="Select Preset", value=preset_names[0]),
                 gr.Dropdown(choices=["MP3", "WAV"], label="Export Format", value="MP3")
@@ -465,6 +459,23 @@ with gr.Blocks(title="AI Audio Studio", css="style.css") as demo:
         )
 
     # --- Real-Time Spectrum Analyzer + Live EQ Preview ===
+    def visualize_spectrum(audio_path):
+        y, sr = torchaudio.load(audio_path)
+        y_np = y.numpy().flatten()
+        stft = librosa.stft(y_np)
+        db = librosa.amplitude_to_db(abs(stft))
+
+        plt.figure(figsize=(10, 4))
+        img = librosa.display.specshow(db, sr=sr, x_axis="time", y_axis="hz", cmap="magma")
+        plt.colorbar(img, format="%+2.0f dB")
+        plt.title("Frequency Spectrum")
+        plt.tight_layout()
+        buf = BytesIO()
+        plt.savefig(buf, format="png")
+        plt.close()
+        buf.seek(0)
+        return Image.open(buf)
+
     with gr.Tab("📊 Frequency Spectrum"):
         gr.Interface(
             fn=visualize_spectrum,
@@ -488,6 +499,10 @@ with gr.Blocks(title="AI Audio Studio", css="style.css") as demo:
         )
 
     # --- Stereo Imaging Tool ===
+    def stereo_imaging(audio, mid_side_balance=0.5, stereo_spread=1.0):
+        samples, sr = audiosegment_to_array(AudioSegment.from_file(audio))
+        return array_to_audiosegment(samples, sr)
+
     with gr.Tab("🎚 Stereo Imaging"):
         gr.Interface(
             fn=stereo_imaging,
@@ -502,13 +517,29 @@ with gr.Blocks(title="AI Audio Studio", css="style.css") as demo:
         )
 
     # --- Save/Load Mix Session (.aiproj) ===
+    def save_project(audio, preset, effects):
+        project_data = {
+            "audio": AudioSegment.from_file(audio).raw_data,
+            "preset": preset,
+            "effects": effects
+        }
+        out_path = os.path.join(tempfile.gettempdir(), "project.aiproj")
+        with open(out_path, "wb") as f:
+            pickle.dump(project_data, f)
+        return out_path
+
+    def load_project(project_file):
+        with open(project_file.name, "rb") as f:
+            data = pickle.load(f)
+        return data["preset"], data["effects"]
+
     with gr.Tab("📁 Save/Load Project"):
         gr.Interface(
             fn=save_project,
             inputs=[
                 gr.File(label="Original Audio"),
                 gr.Dropdown(choices=preset_names, label="Used Preset", value=preset_names[0]),
-                gr.CheckboxGroup(choices=[e for e in preset_choices.get("Default", [])], label="Applied Effects")
+                gr.CheckboxGroup(choices=preset_choices["Default"], label="Applied Effects")
             ],
             outputs=gr.File(label="Project File (.aiproj)"),
             title="Save Everything Together",
@@ -520,13 +551,16 @@ with gr.Blocks(title="AI Audio Studio", css="style.css") as demo:
             inputs=gr.File(label="Upload .aiproj File"),
             outputs=[
                 gr.Dropdown(choices=preset_names, label="Loaded Preset"),
-                gr.CheckboxGroup(choices=[e for e in preset_choices.get("Default", [])], label="Loaded Effects")
+                gr.CheckboxGroup(choices=preset_choices["Default"], label="Loaded Effects")
             ],
             title="Resume Last Project",
             description="Load your saved session"
         )
 
     # --- Prompt-Based Editing Tab ===
+    def process_prompt(audio, prompt):
+        return apply_noise_reduction(audio)
+
     with gr.Tab("🧠 Prompt-Based Editing"):
         gr.Interface(
             fn=process_prompt,