app.py

import gradio as gr
import speech_recognition as sr

def speech_to_text_from_file(audio_file):
    recognizer = sr.Recognizer()
    
    try:
        with sr.AudioFile(audio_file) as source:
            audio = recognizer.record(source)
            text = recognizer.recognize_google(audio)
            return text
    except sr.UnknownValueError:
        return "❌ Could not understand the audio."
    except sr.RequestError:
        return "❌ API unavailable or internet issue."
    except Exception as e:
        return f"❌ Error: {str(e)}"

iface = gr.Interface(
    fn=speech_to_text_from_file,
    inputs=gr.Audio(type="filepath", label="Upload Audio File (WAV/FLAC/AIFF)"),
    outputs=gr.Textbox(label="Transcribed Text"),
    title="🗣️ Speech-to-Text Converter",
    description="Upload an audio file (WAV, FLAC, AIFF) to get a text transcription using Google Speech Recognition.",
    allow_flagging="never"
)

if __name__ == "__main__":
    iface.launch()