Quickstart

pip install kugelaudio

uv add kugelaudio

from kugelaudio import KugelAudio

# Initialize the client
client = KugelAudio(api_key="your_api_key")

# Generate speech
audio = client.tts.generate(
    text="Hello, world!",
    model_id="kugel-3",
    voice_id=1071,
)

# Save to file
audio.save("output.wav")

from kugelaudio.turn import TurnMessage

turn = detector.create_session("en")
turn.update_history([
    TurnMessage("user", "I'd like to book a trip."),
    TurnMessage("assistant", "Where would you like to go?"),
])
turn.update_transcript("To Berlin, and then")
# Feed audio and VAD silence observations through this same session.

import asyncio
from kugelaudio import KugelAudio

async def main():
    # Create a pre-connected client (handshake happens here)
    client = await KugelAudio.create(api_key="your_api_key")
    
    # First request is now fast — no handshake on the hot path
    async for chunk in client.tts.stream_async("Hello, world!", voice_id=1071):
        if hasattr(chunk, 'audio'):
            play_audio(chunk.audio)
    
    await client.aclose()

asyncio.run(main())

from kugelaudio import KugelAudio

client = KugelAudio(api_key="your_api_key")
with client.tts.streaming_session_sync(voice_id=1071) as session:
    for chunk in session.send("Hello, world!"):
        play_audio(chunk.audio)
    for chunk in session.flush():
        play_audio(chunk.audio)

from kugelaudio import KugelAudio

# Initialize client
client = KugelAudio(api_key="your_api_key")

# List available models
print("Available Models:")
for model in client.models.list():
    print(f"  - {model.id}: {model.name}")

# List available voices
print("\nAvailable Voices:")
result = client.voices.list(limit=5)
for voice in result.voices:
    print(f"  - {voice.id}: {voice.name}")

# Generate audio
print("\nGenerating audio...")
audio = client.tts.generate(
    text="Welcome to KugelAudio. This is an example of high-quality text-to-speech synthesis.",
    model_id="kugel-3",
    voice_id=1071,
)

print(f"Generated {audio.duration_seconds:.2f}s of audio in {audio.generation_ms:.0f}ms")
print(f"Real-time factor: {audio.rtf:.2f}x")

# Save to file
audio.save("example.wav")
print("Saved to example.wav")

# Close client
client.close()