Update app.py

app.py

@@ -1 +1,57 @@
- 
+  import os
+import json
+import base64
+import requests
+from flask import Flask, request, send_file
+
+app = Flask(__name__)
+
+API_KEY = os.getenv("GEMINI_API_KEY")
+API_URL = "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-preview-tts:generateContent"
+
+headers = {
+    "Content-Type": "application/json",
+    "x-goog-api-key": API_KEY,
+}
+
+def generate_audio(text):
+    payload = {
+        "contents": [{
+            "parts": [{
+                "text": f"Say cheerfully: {text}"
+            }]
+        }],
+        "generationConfig": {
+            "responseModalities": ["AUDIO"],
+            "speechConfig": {
+                "voiceConfig": {
+                    "prebuiltVoiceConfig": {
+                        "voiceName": "Kore"
+                    }
+                }
+            }
+        }
+    }
+
+    response = requests.post(API_URL, headers=headers, data=json.dumps(payload))
+    if response.status_code != 200:
+        raise Exception(f"API Error: {response.text}")
+
+    res_json = response.json()
+    data = res_json["candidates"][0]["content"]["parts"][0]["inlineData"]["data"]
+    audio_bytes = base64.b64decode(data)
+
+    output_path = "out.wav"
+    with open(output_path, "wb") as f:
+        f.write(audio_bytes)
+
+    return output_path
+
+@app.route("/speak", methods=["POST"])
+def speak():
+    text = request.json.get("text", "Have a wonderful day!")
+    output_path = generate_audio(text)
+    return send_file(output_path, mimetype="audio/wav")
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=7860)