app.py

import gradio as gr
import speech_recognition as sr

def speech_to_text(audio):
    recognizer = sr.Recognizer()
    
    with sr.AudioFile(audio.name) as source:
        audio_data = recognizer.record(source)
        try:
            text = recognizer.recognize_google(audio_data, language="zh-TW")
            return text
        except sr.UnknownValueError:
            return "語音無法識別"
        except sr.RequestError:
            return "無法連接到服務"

iface = gr.Interface(fn=speech_to_text, 
                     inputs=gr.Audio(source="upload", type="file"), 
                     outputs="text",
                     title="語音轉文字系統",
                     description="上傳音頻文件以將語音轉換為文字。")

iface.launch()