add speech to text

app.py

@@ -318,7 +318,29 @@ def text_to_speech_2(text):
     except requests.exceptions.RequestException as e:
         print(f"Error: {e}")
         return None
+
+def speech_to_text(Filename_Audio_input_single):
+    print("Start speech to text ....")
+    access_token = get_azure_access_token()
     
+    if not access_token:
+        return None
+
+    try:
+        endpoint = f"https://eastus.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1?language=en-US"
+        headers={
+            "Authorization": f"Bearer {access_token}",
+            "Content-Type": "audio/wav",}
+
+        response = requests.post(endpoint, headers=headers, data=open(Filename_Audio_input_single, "rb"))
+        print("Speech to Text: ", response.text)
+        text_from_audio = response.txt
+        return text_from_audio
+    except requests.exceptions.RequestException as e:
+        print(f"Error speech_to_text: {e}")
+        return None
+
+
 Text2Sound_tool = Tool(
     name = "Text_To_Sound_REST_API",
     # func = Text2Sound,
@@ -958,6 +980,7 @@ with gr.Blocks() as demo:
     upload_button.upload(func_upload_file, [upload_button, chatbot], chatbot)
     agentchoice.change(SetAgent, agentchoice, None)
     frash_logs.click(read_logs, None, logs)
+    voice_input.stop_recording(speech_to_text, voice_input, None)
     # voice_output.end(ClearAudio, None, voice_output)
     # def clear_voice():
     #     print("clear audio ...")