Text-to-Speech

import requests

def text_to_speech(text, model="Kokoro-82m", voice=None, **kwargs):
    headers = {
        "x-api-key": "YOUR_API_KEY",
        "Content-Type": "application/json"
    }
    
    payload = {
        "text": text,
        "model": model
    }
    
    if voice:
        payload["voice"] = voice
    
    payload.update(kwargs)
    
    response = requests.post(
        "https://nano-gpt.com/api/tts",
        headers=headers,
        json=payload
    )
    
    if response.status_code == 200:
        content_type = response.headers.get('content-type', '')
        
        if 'application/json' in content_type:
            # JSON response with audio URL
            data = response.json()
            audio_response = requests.get(data['audioUrl'])
            with open('output.wav', 'wb') as f:
                f.write(audio_response.content)
        else:
            # Binary audio data (OpenAI models)
            with open('output.mp3', 'wb') as f:
                f.write(response.content)
        
        return response
    else:
        raise Exception(f"Error: {response.status_code}")

# Basic usage
text_to_speech(
    "Hello! Welcome to our service.",
    model="Kokoro-82m",
    voice="af_bella"
)

# Popular voice examples by category
voices = {
    "american_female": ["af_bella", "af_nova", "af_aoede"],
    "american_male": ["am_adam", "am_onyx", "am_eric"],
    "british_female": ["bf_alice", "bf_emma"],
    "british_male": ["bm_daniel", "bm_george"],
    "japanese_female": ["jf_alpha", "jf_gongitsune"],
    "chinese_female": ["zf_xiaoxiao", "zf_xiaoyi"],
    "french_female": ["ff_siwis"],
    "italian_male": ["im_nicola"]
}

# Generate multilingual samples
samples = [
    {"text": "Hello, welcome!", "voice": "af_bella", "lang": "English"},
    {"text": "Bonjour et bienvenue!", "voice": "ff_siwis", "lang": "French"},
    {"text": "こんにちは！", "voice": "jf_alpha", "lang": "Japanese"},
    {"text": "你好，欢迎！", "voice": "zf_xiaoxiao", "lang": "Chinese"}
]

for sample in samples:
    text_to_speech(
        text=sample["text"],
        model="Kokoro-82m",
        voice=sample["voice"]
    )

# Stable, consistent voice
text_to_speech(
    text="This is a professional announcement.",
    model="Elevenlabs-Turbo-V2.5",
    voice="Rachel",
    stability=0.9,
    similarity_boost=0.8,
    style=0
)

# Expressive, dynamic voice  
text_to_speech(
    text="This is so exciting!",
    model="Elevenlabs-Turbo-V2.5",
    voice="Rachel",
    stability=0.3,
    similarity_boost=0.7,
    style=0.8,
    speed=1.2
)

# Available voices: Rachel, Adam, Bella, Brian, etc.

# High-definition with voice instructions
text_to_speech(
    text="Welcome to customer service.",
    model="tts-1-hd",
    voice="nova",
    instructions="Speak warmly and professionally like a customer service representative",
    response_format="flac"
)

# Ultra-low cost option
text_to_speech(
    text="This is a cost-effective option.",
    model="gpt-4o-mini-tts",
    voice="alloy",
    instructions="Speak clearly and cheerfully",
    response_format="mp3"
)

# Different format examples
formats = ["mp3", "wav", "opus", "flac", "aac"]
for fmt in formats:
    text_to_speech(
        text=f"This is {fmt.upper()} format.",
        model="tts-1",
        voice="echo",
        response_format=fmt
    )

try:
    result = text_to_speech("Hello world!", model="Kokoro-82m")
    print("Success!")
except Exception as e:
    if "400" in str(e):
        print("Bad request - check parameters")
    elif "401" in str(e):
        print("Unauthorized - check API key")
    elif "413" in str(e):
        print("Text too long for model")
    else:
        print(f"Error: {e}")