text.py

#!/usr/bin/env python3
import sys
import requests

# Base URL of your running server. Adjust the port if needed.
BASE_URL = "http://172.21.207.14:5000/"

def check_api_health():
    """Call the /api/health endpoint and display the result."""
    try:
        response = requests.get(f"{BASE_URL}/api/health")
        if response.status_code == 200:
            data = response.json()
            print("API Health:", data)
        else:
            print("Error:", response.text)
    except Exception as e:
        print("Error connecting to API Health endpoint:", e)

def check_voices():
    """Call the /api/voices endpoint and list available voices."""
    try:
        response = requests.get(f"{BASE_URL}/api/voices")
        if response.status_code == 200:
            data = response.json()
            voices = data.get("voices", [])
            default_voice = data.get("default", "None")
            print("\nDefault Voice:", default_voice)
            print("Available Voices:")
            for voice in voices:
                print(" -", voice)
        else:
            print("Error:", response.text)
    except Exception as e:
        print("Error connecting to API Voices endpoint:", e)

def generate_speech():
    """Prompt for text and parameters, call the /api/tts endpoint, and save the generated audio."""
    text = input("Enter text to convert to speech: ").strip()
    if not text:
        print("Error: Text cannot be empty.")
        return

    voice = input("Enter voice to use (leave blank for default): ").strip()
    if voice == "":
        # Get the default voice from the voices endpoint
        try:
            response = requests.get(f"{BASE_URL}/api/voices")
            if response.status_code == 200:
                voice = response.json().get("default", "")
                print(f"Using default voice: {voice}")
            else:
                print("Unable to get default voice. Using empty voice name.")
        except Exception as e:
            print("Error getting default voice:", e)

    output_format = input("Enter output format (wav/mp3/aac, default: wav): ").strip().lower() or "wav"
    try:
        speed = float(input("Enter speech speed (default: 1.0): ").strip() or 1.0)
    except ValueError:
        print("Invalid speed input. Using default speed 1.0.")
        speed = 1.0

    payload = {
        "text": text,
        "voice": voice,
        "format": output_format,
        "speed": speed
    }

    print("\nGenerating speech...")
    try:
        response = requests.post(f"{BASE_URL}/api/tts", json=payload)
        if response.status_code == 200:
            content_type = response.headers.get("Content-Type", "")
            filename = f"output.{output_format}"
            with open(filename, "wb") as f:
                f.write(response.content)
            print(f"Audio generated and saved as '{filename}' (Content-Type: {content_type})")
        else:
            print("Error generating speech:", response.text)
    except Exception as e:
        print("Error connecting to API TTS endpoint:", e)

def main():
    while True:
        print("\n==== Kokoro-TTS CLI Test ====")
        print("1. Check API Health")
        print("2. Check Voices")
        print("3. Generate Speech")
        print("4. Quit")
        choice = input("Select an option (1-4): ").strip()

        if choice == "1":
            check_api_health()
        elif choice == "2":
            check_voices()
        elif choice == "3":
            generate_speech()
        elif choice == "4":
            print("Exiting.")
            sys.exit(0)
        else:
            print("Invalid option. Please choose a number between 1 and 4.")

if __name__ == "__main__":
    main()