Update app.py

app.py

@@ -1,26 +1,37 @@
-# app.py
+from flask import Flask, request, jsonify, send_file from flask_cors import CORS from audio_generation import generate_audio import os import tempfile from werkzeug.utils import secure_filename import pytesseract from PIL import Image
 
-from flask import Flask, request, jsonify, send_file
-from flask_cors import CORS
-from audio_generation import generate_audio
-import os
+app = Flask(__name__) CORS(app)
 
-app = Flask(__name__)
-CORS(app)
+UPLOAD_FOLDER = tempfile.gettempdir() app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
 
-@app.route("/")
-def index():
-    return "Bark TTS API is running."
+@app.route("/upload", methods=["POST"]) def upload_file(): if 'file' not in request.files: return jsonify({"error": "No file part"}), 400
 
-@app.route("/speak", methods=["POST"])
-def speak():
-    data = request.json
-    text = data.get("text", "")
-    if not text:
-        return jsonify({"error": "No text provided"}), 400
+file = request.files['file']
+if file.filename == '':
+    return jsonify({"error": "No selected file"}), 400
 
-    audio_path = generate_audio(text)
-    return send_file(audio_path, mimetype="audio/wav")
+filename = secure_filename(file.filename)
+filepath = os.path.join(app.config['UPLOAD_FOLDER'], filename)
+file.save(filepath)
 
-if __name__ == "__main__":
+ext = os.path.splitext(filename)[1].lower()
+if ext in ['.png', '.jpg', '.jpeg', '.bmp']:
+    text = pytesseract.image_to_string(Image.open(filepath))
+elif ext in ['.txt']:
+    with open(filepath, 'r', encoding='utf-8') as f:
+        text = f.read()
+else:
+    text = "[Unsupported file type for text extraction]"
+
+return jsonify({"text": text})
+
+@app.route("/speak", methods=["POST"]) def speak(): data = request.get_json() text = data.get("text", "")
+
+if not text:
+    return jsonify({"error": "No text provided"}), 400
+
+audio_path = generate_audio(text)
+return send_file(audio_path, mimetype='audio/wav', as_attachment=False)
+
+if __name__ == "__main__": 
     app.run(host="0.0.0.0", port=7860)