app.py

import gradio as gr
# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")

narrator = pipeline("text-to-speech", model="kakao-enterprise/vits-ljs")

def launch(input):
    # Step 1: Extract text from image
    caption = pipe(input_image)[0]['generated_text']

    # Step 2: Generate speech from the caption
    audio_output = narrator(caption)

    # Step 3: Save the audio to a temporary file
    audio_data = audio_output["audio"]
    sampling_rate = audio_output["sampling_rate"]

    # Gradio expects a tuple: (numpy_array, sampling_rate)
    return (np.array(audio_data), sampling_rate)

iface = gr.Interface(launch,
    fn=launch,
    inputs=gr.Image(type='pil'),
    outputs=gr.Audio(type="numpy", label="Narrated Output"),
    title="SeeSay",
    description="Upload an image to hear its context narrated aloud."
                    )

iface.launch()