# Using OpenAI's Python library
from openai import OpenAI
client = OpenAI(base_url="http://localhost:8880/v1", api_key="not-needed")
response = client.audio.speech.create(
    model="kokoro",  # Not used but required for compatibility, also accepts library defaults
    voice="af_bella+af_sky",
    input="Hello world!",
    response_format="mp3"
)

response.stream_to_file("output.mp3")

import requests


response = requests.get("http://localhost:8880/v1/audio/voices")
voices = response.json()["voices"]

# Generate audio
response = requests.post(
    "http://localhost:8880/v1/audio/speech",
    json={
        "model": "kokoro",  # Not used but required for compatibility
        "input": "Hello world!",
        "voice": "af_bella",
        "response_format": "mp3",  # Supported: mp3, wav, opus, flac
        "speed": 1.0
    }
)

# Save audio
with open("output.mp3", "wb") as f:
    f.write(response.content)

import requests
response = requests.get("http://localhost:8880/v1/audio/voices")
voices = response.json()["voices"]

# Create combined voice (saves locally on server)
response = requests.post(
    "http://localhost:8880/v1/audio/voices/combine",
    json=[voices[0], voices[1]]
)
combined_voice = response.json()["voice"]

# Generate audio with combined voice (or, simply pass multiple directly with `+` )
response = requests.post(
    "http://localhost:8880/v1/audio/speech",
    json={
        "input": "Hello world!",
        "voice": combined_voice, # or skip the above step with f"{voices[0]}+{voices[1]}"
        "response_format": "mp3"
    }
)

# OpenAI-compatible streaming
from openai import OpenAI
client = OpenAI(
    base_url="http://localhost:8880", api_key="not-needed")

# Stream to file
with client.audio.speech.with_streaming_response.create(
    model="kokoro",
    voice="af_bella",
    input="Hello world!"
) as response:
    response.stream_to_file("output.mp3")

# Stream to speakers (requires PyAudio)
import pyaudio
player = pyaudio.PyAudio().open(
    format=pyaudio.paInt16, 
    channels=1, 
    rate=24000, 
    output=True
)

with client.audio.speech.with_streaming_response.create(
    model="kokoro",
    voice="af_bella",
    response_format="pcm",
    input="Hello world!"
) as response:
    for chunk in response.iter_bytes(chunk_size=1024):
        player.write(chunk)

import requests

response = requests.post(
    "http://localhost:8880/v1/audio/speech",
    json={
        "input": "Hello world!",
        "voice": "af_bella",
        "response_format": "pcm"
    },
    stream=True
)

for chunk in response.iter_content(chunk_size=1024):
    if chunk:
        # Process streaming chunks
        pass

import requests

# Convert text to phonemes
response = requests.post(
    "http://localhost:8880/dev/phonemize",
    json={
        "text": "Hello world!",
        "language": "a"  # "a" for American English
    }
)
result = response.json()
phonemes = result["phonemes"]  # Phoneme string e.g  ðɪs ɪz ˈoʊnli ɐ tˈɛst
tokens = result["tokens"]      # Token IDs including start/end tokens 

# Generate audio from phonemes
response = requests.post(
    "http://localhost:8880/dev/generate_from_phonemes",
    json={
        "phonemes": phonemes,
        "voice": "af_bella",
        "speed": 1.0
    }
)

# Save WAV audio
with open("speech.wav", "wb") as f:
    f.write(response.content)