app.py

import gradio as gr
import speech_recognition as sr

def transcribe_audio(file_info):
    recognizer = sr.Recognizer()
    audio_file = file_info['content']

    with sr.AudioFile(audio_file) as source:
        audio_data = recognizer.record(source)
    try:
        text = recognizer.recognize_google(audio_data)
        return text
    except Exception as e:
        return f"Error: {str(e)}"

iface = gr.Interface(
    fn=transcribe_audio,
    inputs=gr.inputs.Audio(source="microphone", type="file"),
    outputs="text"
)

iface.launch()