OpenAI text to speech with the tts-1-hd model

tts.py

#!/usr/bin/env python3
"""Simple text-to-speech script using OpenAI's TTS API."""

import argparse
from pathlib import Path

from dotenv import load_dotenv
from openai import OpenAI

load_dotenv()


def text_to_speech(text: str, output_file: str = "output.mp3", voice: str = "alloy"):
    """Convert text to speech and save to a file.

    Args:
        text: The text to convert to speech.
        output_file: Output audio file path.
        voice: Voice to use (alloy, echo, fable, onyx, nova, shimmer).
    """
    client = OpenAI()

    with client.audio.speech.with_streaming_response.create(
        model="tts-1-hd",
        voice=voice,
        input=text,
    ) as response:
        response.stream_to_file(Path(output_file))
    print(f"Audio saved to {output_file}")


def main():
    parser = argparse.ArgumentParser(description="Convert text to speech using OpenAI")
    parser.add_argument("text", nargs="?", help="Text to convert to speech")
    parser.add_argument("-o", "--output", default="output.mp3", help="Output file path")
    parser.add_argument(
        "-v", "--voice",
        default="shimmer",
        choices=["alloy", "echo", "fable", "onyx", "nova", "shimmer"],
        help="Voice to use",
    )
    parser.add_argument("-f", "--file", help="Read text from a file")

    args = parser.parse_args()

    if args.file:
        text = Path(args.file).read_text()
    elif args.text:
        text = args.text
    else:
        print("Enter text (Ctrl+D to finish):")
        import sys
        text = sys.stdin.read()

    if not text.strip():
        print("Error: No text provided")
        return 1

    text_to_speech(text, args.output, args.voice)
    return 0


if __name__ == "__main__":
    exit(main())