Transform Text intoHuman-Like SpeechInstantly

from openai import OpenAI

# Initialize the client with our API endpoint
client = OpenAI(
    base_url="http://216.249.100.66:13524/v1",
    api_key="free-trial"  # Get your API key at readbyear.com/dashboard
)

# Stream to file
with client.audio.speech.with_streaming_response.create(
    voice="af_bella+em_santa",  # Single voice or multiple voice combo
    input="Hello world!"
) as response:
    response.stream_to_file("output.mp3")

import requests
import numpy as np
import sounddevice as sd
import wave
import os

# Initialize audio stream
sample_rate = 24000
stream = sd.OutputStream(
    samplerate=sample_rate,
    channels=1,
    dtype=np.int16,
    blocksize=1024,
    latency="low"
)
stream.start()

try:
    # Make the API request
    response = requests.post(
        "http://216.249.100.66:13524/v1/audio/speech",
        headers={
            "Authorization": "Bearer free-trial"  # Get your API key at readbyear.com/dashboard
        },
        json={
            "input": "Hello world!",
            "voice": "af_bella",      # Single voice or combined voices: "em_santa+em_alex"
            "response_format": "pcm",  # Use PCM for streaming
            "stream": True,           # Enable streaming
            "lang_code": "e"          # Language code: e (English), s (Spanish), etc.
        },
        stream=True
    )
    response.raise_for_status()

    # Process the streaming response
    for chunk in response.iter_content(chunk_size=1024):
        audio_chunk = np.frombuffer(chunk, dtype=np.int16)
        stream.write(audio_chunk)     # Play audio in real-time

except requests.RequestException as e:
    print(f"Error making request: {e}")
finally:
    # Clean up
    stream.stop()
    stream.close()