app.py

import gradio as gr

fastspeech = gr.Interface.load("huggingface/facebook/fastspeech2-en-ljspeech")
clip = gr.Interface.load("spaces/DrishtiSharma/Text-to-Image-search-using-CLIP")


def text2speech(text):
    return fastspeech(text)


def text2image(text):
    image = clip(text)[0]
    return gr.processing_utils.decode_base64_to_image(image)


block = gr.Blocks()

with block:
    text = gr.inputs.Textbox(placeholder="Try writing something..")

    with gr.Column():
        with gr.Row():
            get_audio = gr.Button("generate audio")
            get_image = gr.Button("generate image")
        with gr.Row():
            speech = gr.outputs.Audio()
            image = gr.outputs.Image()


    get_audio.click(text2speech, inputs=text, outputs=speech)
    get_image.click(text2image, inputs=text, outputs=image)

block.launch()