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)
    out_tts = tts_pipe(out[0]['generated_text'])
    return out[0]['generated_text'], (out_tts["sampling_rate"],out_tts["audio"][0])


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