Update openai_tts_tool.py

openai_tts_tool.py

@@ -1,29 +1,57 @@
-import openai
+from openai import OpenAI
+import tempfile
+import os
 
 def generate_audio_and_text(api_key, input_text, model_name, voice_type, voice_speed, language, output_option, summary_length, additional_prompt):
-    # Set API key dynamically
-    openai.api_key = api_key
-    client = openai.OpenAI(api_key=api_key)
-
-    # Assuming text-to-speech and summarization logic goes here
-    if output_option in ["summary_text", "both"]:
-        text_summary = f"Generated summary for: {input_text[:100]}..."  # Replace with real summary generation logic
-
-    if output_option in ["audio", "both"]:
-        response = client.audio.speech.create(
-            text=input_text,
-            model=model_name,
-            voice=voice_type,
-            language=language,
-            speed=voice_speed
-        )
-        audio_output = response['audio_file']  # Placeholder for the actual audio file output
-
-    if output_option == "summary_text":
-        return text_summary, None
-    elif output_option == "audio":
-        return None, audio_output
-    elif output_option == "both":
-        return text_summary, audio_output
-
-    return None, None
+    if not input_text:
+        return None, "No input text provided"
+    
+    try:
+        client = OpenAI(api_key=api_key)
+        
+        # Generate summary if requested
+        summary_text = None
+        if output_option in ["summary_text", "both"]:
+            summary_prompt = f"Summarize the following text in approximately {summary_length} words. {additional_prompt or ''}\n\nText: {input_text}"
+            
+            summary_response = client.chat.completions.create(
+                model=model_name,
+                messages=[{"role": "user", "content": summary_prompt}]
+            )
+            summary_text = summary_response.choices[0].message.content
+        
+        # Generate audio if requested
+        audio_file = None
+        if output_option in ["audio", "both"]:
+            speech_response = client.audio.speech.create(
+                model="tts-1",  # or "tts-1-hd" for higher quality
+                voice=voice_type,
+                input=input_text,
+                speed=float(voice_speed)
+            )
+            
+            # Create temp directory if it doesn't exist
+            temp_dir = os.path.join(os.getcwd(), 'temp')
+            if not os.path.exists(temp_dir):
+                os.makedirs(temp_dir)
+            
+            # Save the audio to a temporary file
+            audio_path = os.path.join(temp_dir, f"output_{hash(input_text)}.mp3")
+            with open(audio_path, "wb") as f:
+                for chunk in speech_response.iter_bytes():
+                    f.write(chunk)
+            
+            audio_file = audio_path
+        
+        # Return based on output option
+        if output_option == "summary_text":
+            return None, summary_text
+        elif output_option == "audio":
+            return audio_file, None
+        elif output_option == "both":
+            return audio_file, summary_text
+            
+    except Exception as e:
+        return None, f"Error: {str(e)}"
+    
+    return None, None