text_to_speech.py

import gc
from os import getenv
import gradio as gr
from transformers import pipeline
from utils import spaces_gpu


@spaces_gpu
def text_to_speech(text: str) -> tuple[int, bytes]:
    """Convert text to speech audio using a TTS (Text-to-Speech) model.
    
    This function uses a transformer pipeline to generate speech audio from
    text input. The model is loaded, inference is performed, and then cleaned
    up to free GPU memory.
    
    Args:
        text: Input text string to convert to speech.
    
    Returns:
        Tuple containing:
            - int: Sampling rate of the generated audio (e.g., 22050 Hz)
            - bytes: Raw audio data as bytes
    
    Note:
        - The model ID is determined by the TEXT_TO_SPEECH_MODEL environment variable.
        - Uses safetensors for secure model loading.
        - Automatically selects the best available device (CUDA/XPU/MPS/CPU).
        - Cleans up model and GPU memory after inference.
        - Returns audio in format compatible with Gradio Audio component.
    """
    narrator = pipeline(
        "text-to-speech",
        getenv("TEXT_TO_SPEECH_MODEL"),
        model_kwargs={"use_safetensors": True} # Use safetensors to avoid torch.load restriction.
    )
    result = narrator(text)
    del narrator
    gc.collect()
    return (result["sampling_rate"], result["audio"][0])


def create_text_to_speech_tab():
    """Create the text-to-speech tab in the Gradio interface.
    
    This function sets up all UI components for text-to-speech generation,
    including input textbox, generate button, and output audio player.
    """
    gr.Markdown("Generate speech from text.")
    text_to_speech_text = gr.Textbox(label="Text")
    text_to_speech_generate_button = gr.Button("Generate")
    text_to_speech_output = gr.Audio(label="Speech")
    text_to_speech_generate_button.click(
        fn=text_to_speech,
        inputs=text_to_speech_text,
        outputs=text_to_speech_output
    )