This is a simple implementation of transcription with OpenAI Whisper API and Gradio.

whisper-simple.py

import gradio as gr
from openai import OpenAI
import os

client = OpenAI(
    api_key=os.getenv("OPENAI_API_KEY"),
)
DEFAULT_PROMPT = (
    "Hello, welcome to my lecture."  # To make sure transcription has punctuation
)


def transcribe(audio_file, prompt):
    prompt = prompt if prompt else DEFAULT_PROMPT

    try:
        with open(audio_file, "rb") as file:
            response = client.audio.transcriptions.create(
                file=file,
                model="whisper-1",
                prompt=prompt,
                temperature=0.2,
                language="en",  # ja for Japanese
                response_format="text",
            )
        return response
    except Exception as e:
        return f"An error occurred: {str(e)}"


# Gradio interface
iface = gr.Interface(
    fn=transcribe,
    inputs=[
        gr.Audio(sources=["upload"], type="filepath"),
        gr.Textbox(label="Whisper Model Prompt"),
    ],
    outputs="text",
)

# Run the Gradio app
iface.launch(debug=True)