Update app.py

app.py

@@ -7,47 +7,41 @@ import os
 API_KEY = os.getenv('PLAY_API_KEY')
 USER_ID = os.getenv('PLAY_USER_ID')
 
-# Function to interact with Play.ht API
-def text_to_audio(text):
-    url = "https://play.ht/api/v2/tts"
-
+def text_to_speech(text):
+    url = "https://api.play.ht/api/v2/tts/stream"
+    
+    # Customize the payload based on your Play.ht account setup
+    payload = {
+        "voice": "s3://voice-cloning-zero-shot/d9ff78ba-d016-47f6-b0ef-dd630f59414e/female-cs/manifest.json", # Replace with your desired voice
+        "output_format": "mp3",
+        "content": text  # Text to be converted to speech
+    }
     headers = {
+        "accept": "audio/mpeg",
+        "content-type": "application/json",
         "Authorization": API_KEY,
-        "X-User-ID": USER_ID,
-        "Content-Type": "application/json"
+        "X-User-ID": USER_ID
     }
-
-    # Customize options here (e.g., voice, language, etc.)
-    data = {
-        "voice": "en_us-male-1",  # Specify a voice of choice
-        "content": [text],
-        "speed": 1.0,
-        "sample_rate": 24000,
-    }
-
-    response = requests.post(url, headers=headers, json=data)
     
-    if response.status_code == 201:
-        response_data = response.json()
-        audio_url = response_data.get("audio_url")
-        
-        # Fetch the audio file
-        audio_response = requests.get(audio_url)
+    response = requests.post(url, json=payload, headers=headers)
+    
+    # Check if the response was successful
+    if response.status_code == 200:
+        # Save the audio content to a file
         audio_path = "output_audio.mp3"
         with open(audio_path, "wb") as audio_file:
-            audio_file.write(audio_response.content)
-        
+            audio_file.write(response.content)
         return audio_path
     else:
-        return f"Error: {response.status_code}, {response.text}"
+        return f"Error: {response.status_code} - {response.text}"
 
-# Gradio app interface
+# Set up Gradio Interface
 iface = gr.Interface(
-    fn=text_to_audio,
+    fn=text_to_speech,
     inputs="text",
     outputs="audio",
-    title="Text to Speech with Play.ht",
-    description="Convert text into realistic speech using Play.ht."
+    title="Play.ht Text-to-Speech",
+    description="Convert text into speech using Play.ht's TTS streaming API."
 )
 
 iface.launch(debug = True)