Update app.py

app.py

@@ -4,11 +4,17 @@ import tempfile
 import os
 from openai import OpenAI
 import soundfile as sf
+import requests
+import json
 
 # Initialize OpenAI client
 client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"))
 
-def text_to_speech_with_emotion(text, voice, model):
+# ChatTTS API endpoint and key
+CHATTTS_API_ENDPOINT = "https://api.chattts.com/v1/generate"
+CHATTTS_API_KEY = os.environ.get("CHATTTS_API_KEY")
+
+def openai_tts(text, voice, model):
     try:
         response = client.audio.speech.create(
             model=model,
@@ -21,9 +27,32 @@ def text_to_speech_with_emotion(text, voice, model):
             temp_audio.write(response.content)
             temp_audio_path = temp_audio.name
 
-        return temp_audio_path, f"Speech generated with {voice} voice using {model} model"
+        return temp_audio_path, f"Speech generated with OpenAI TTS using {voice} voice and {model} model"
     except Exception as e:
-        return None, f"Error in speech generation: {str(e)}"
+        return None, f"Error in OpenAI TTS speech generation: {str(e)}"
+
+def chattts(text, voice, style):
+    try:
+        payload = {
+            "text": text,
+            "voice": voice,
+            "style": style
+        }
+        headers = {
+            "Content-Type": "application/json",
+            "Authorization": f"Bearer {CHATTTS_API_KEY}"
+        }
+        response = requests.post(CHATTTS_API_ENDPOINT, json=payload, headers=headers)
+        response.raise_for_status()
+
+        # Save the audio to a temporary file
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as temp_audio:
+            temp_audio.write(response.content)
+            temp_audio_path = temp_audio.name
+
+        return temp_audio_path, f"Speech generated with ChatTTS using {voice} voice and {style} style"
+    except Exception as e:
+        return None, f"Error in ChatTTS speech generation: {str(e)}"
 
 def generate_simple_sound(description, duration, frequency):
     try:
@@ -51,12 +80,22 @@ def generate_simple_sound(description, duration, frequency):
 
 # Gradio interface
 with gr.Blocks() as iface:
-    gr.Markdown("# OpenAI TTS and Simple Sound Generation Tool")
+    gr.Markdown("# OpenAI TTS, ChatTTS, and Simple Sound Generation Tool")
     
     with gr.Tab("Text-to-Speech"):
         text_input = gr.Textbox(label="Enter text for speech generation")
-        voice_input = gr.Dropdown(["alloy", "echo", "fable", "onyx", "nova", "shimmer"], label="Select Voice", value="nova")
-        model_input = gr.Dropdown(["tts-1", "tts-1-hd"], label="Select Model", value="tts-1")
+        tts_method = gr.Radio(["OpenAI TTS", "ChatTTS"], label="TTS Method", value="OpenAI TTS")
+        
+        with gr.Group():
+            gr.Markdown("OpenAI TTS Options")
+            openai_voice_input = gr.Dropdown(["alloy", "echo", "fable", "onyx", "nova", "shimmer"], label="Select Voice", value="nova")
+            openai_model_input = gr.Dropdown(["tts-1", "tts-1-hd"], label="Select Model", value="tts-1")
+        
+        with gr.Group():
+            gr.Markdown("ChatTTS Options")
+            chattts_voice_input = gr.Dropdown(["en-US-1", "en-US-2", "en-GB-1", "en-GB-2"], label="Select Voice", value="en-US-1")
+            chattts_style_input = gr.Dropdown(["neutral", "happy", "sad", "angry", "fearful", "disgusted", "surprised"], label="Select Style", value="neutral")
+        
         speech_button = gr.Button("Generate Speech")
         speech_output = gr.Audio(label="Generated Speech")
         speech_message = gr.Textbox(label="Message")
@@ -69,8 +108,14 @@ with gr.Blocks() as iface:
         sound_output = gr.Audio(label="Generated Sound")
         sound_message = gr.Textbox(label="Message")
 
-    speech_button.click(text_to_speech_with_emotion, 
-                        inputs=[text_input, voice_input, model_input], 
+    def generate_speech(text, method, openai_voice, openai_model, chattts_voice, chattts_style):
+        if method == "OpenAI TTS":
+            return openai_tts(text, openai_voice, openai_model)
+        else:
+            return chattts(text, chattts_voice, chattts_style)
+
+    speech_button.click(generate_speech, 
+                        inputs=[text_input, tts_method, openai_voice_input, openai_model_input, chattts_voice_input, chattts_style_input], 
                         outputs=[speech_output, speech_message])
     sound_button.click(generate_simple_sound, 
                        inputs=[prompt_input, duration_input, frequency_input],