Create app.py

app.py

@@ -0,0 +1,53 @@
+import gradio as gr
+import time
+import wave
+from google import genai
+from google.genai import types
+from google.colab import userdata
+
+# Set up the wave file to save the output:
+def wave_file(filename, pcm, channels=1, rate=24000, sample_width=2):
+   with wave.open(filename, "wb") as wf:
+      wf.setnchannels(channels)
+      wf.setsampwidth(sample_width)
+      wf.setframerate(rate)
+      wf.writeframes(pcm)
+
+# Retrieve the API key from Colab's Secrets Manage
+GOOGLE_API_KEY = userdata.get('GOOGLE_API_KEY')
+client = genai.Client(api_key=GOOGLE_API_KEY)
+
+def synthesize_speech(text):
+    """Synthesizes speech from the given text and saves it to a wave file."""
+    response = client.models.generate_content(
+        model="gemini-2.5-flash-preview-tts",
+        contents=f"Say cheerfully: {text}",
+        config=types.GenerateContentConfig(
+            response_modalities=["AUDIO"],
+            speech_config=types.SpeechConfig(
+                voice_config=types.VoiceConfig(
+                    prebuilt_voice_config=types.PrebuiltVoiceConfig(
+                        voice_name='Kore',
+                    )
+                )
+            ),
+        )
+    )
+
+    data = response.candidates[0].content.parts[0].inline_data.data
+
+    # Create a dynamic filename using a timestamp
+    timestamp = int(time.time())
+    file_name = f'out_{timestamp}.wav'
+    wave_file(file_name, data)
+
+    return file_name
+
+iface = gr.Interface(
+    fn=synthesize_speech,
+    inputs=gr.Textbox(label="Enter text for speech synthesis"),
+    outputs=gr.Audio(label="Generated Audio"),
+    title="Text-to-Speech Interface"
+)
+
+iface.launch()