app.py

import os
import gradio as gr
from transformers import pipeline
from IPython.display import Audio as IPythonAudio

pipe = pipeline("image-to-text",
                model="Salesforce/blip-image-captioning-base")
tts_pipe = pipeline("text-to-speech",
                    model="kakao-enterprise/vits-ljs")

def launch(input):
    out = pipe(input)
    narrated_text = tts_pipe(out[0]['generated_text'])
    IPythonAudio(narrated_text["audio"][0],
             rate=narrated_text["sampling_rate"])
    return out[0]['generated_text']

iface = gr.Interface(launch,
                     inputs=gr.Image(type='pil'),
                     outputs="text")
iface.launch()