Update backend/open_webui/apps/audio/main.py

backend/open_webui/apps/audio/main.py

@@ -7,6 +7,7 @@ from functools import lru_cache
 from pathlib import Path
 from pydub import AudioSegment
 from pydub.silence import split_on_silence
+from gradio_client import Client, file
 
 import requests
 from open_webui.config import (
@@ -252,25 +253,36 @@ async def speech(request: Request, user=Depends(get_verified_user)):
             body = body.decode("utf-8")
             body = json.loads(body)
             body["model"] = app.state.config.TTS_MODEL
+            query=body["input"]
+            print(query)
             body = json.dumps(body).encode("utf-8")
         except Exception:
             pass
 
         r = None
         try:
-            r = requests.post(
-                url=f"{app.state.config.TTS_OPENAI_API_BASE_URL}/audio/speech",
-                data=body,
-                headers=headers,
-                stream=True,
+            client = Client("https://s5k.cn/api/v1/studio/iic/CosyVoice-300M-WAIC/gradio/")
+            r= client.predict(
+		          _sound_radio="中文女",
+		          _synthetic_input_textbox={"query":query},
+		          _seed=0,
+		          api_name="/generate_audio"
+
             )
 
-            r.raise_for_status()
+            #r = requests.post(
+               # url=f"{app.state.config.TTS_OPENAI_API_BASE_URL}/audio/speech",
+                #data=body,
+               # headers=headers,
+               # stream=True,
+            #)
+
+           # r.raise_for_status()
 
             # Save the streaming content to a file
             with open(file_path, "wb") as f:
-                for chunk in r.iter_content(chunk_size=8192):
-                    f.write(chunk)
+               # for chunk in r.iter_content(chunk_size=8192):
+                    f.write(r.content)
 
             with open(file_body_path, "w") as f:
                 json.dump(json.loads(body.decode("utf-8")), f)