Text to Speech

export OPENAI_API_KEY="your_openai_api_key"

import os
from gtts import gTTS
from openai import OpenAI

client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))

prompt = "Tell me a story about a brave knight who loves basketball."

def text_to_speech(text: str, lang: str = "en", slow: bool = False) -> None:
    """
    Generate speech from text using gTTS, save as MP3, and play it.
    """
    tts = gTTS(text=text, lang=lang, slow=slow)
    filename = "tts_output.mp3"
    tts.save(filename)
    # macOS uses 'afplay'; Linux users can install 'mpg123' or 'mpg321'
    os.system(f"afplay {filename}")

def generate_text(
    prompt: str,
    model: str = "gpt-3.5-turbo",
    temperature: float = 0.8,
    max_tokens: int = 150
) -> str:
    """
    Generate a chat completion for the given prompt.
    """
    response = client.chat.completions.create(
        model=model,
        messages=[{"role": "user", "content": prompt}],
        temperature=temperature,
        max_tokens=max_tokens
    )
    return response.choices[0].message.content

def gen_and_speak(prompt: str) -> None:
    """
    Generate text from the prompt, display it, and play the speech.
    """
    text = generate_text(prompt)
    print("Generated Text:\n")
    print(text, "\n")
    text_to_speech(text)

if __name__ == "__main__":
    gen_and_speak(prompt)

$ python3 text_to_speech_pipeline.py
Generated Text:

Once upon a time in the kingdom of Eldoria, there lived a brave knight named Sir Cedric...
# (Audio will start playing automatically)