非推奨モデル

your_api_key: str = ""

client = Cartesia(api_key=your_api_key)

print("Cloning a voice")
with open("3 to 10 seconds of source audio.wav", mode="rb") as f:
    voice = client.voices.clone(
        clip=f,
        # this must match the source audio
        language="en",
        name="My Voice",
        mode="similarity",
)
print(f"Cloned voice {voice.id}")

print("Generating audio...")
generated_audio = client.tts.bytes(
    # voice embeddings will not work after June 1, 2026!
    voice={"mode": "id", "id": voice.id},
    model_id="sonic-3.5",
    transcript="Hello from Cartesia!",
    language="en",
    output_format={
        "container": "wav",
        "encoding": "pcm_f32le",
        "sample_rate": 44100
    },
)

{
  "voice": {
    "mode": "embedding",
    "embedding": [1, 2, ..., 3, 4]
  },
  "model_id": "sonic-2",
  // ...
}

{
  "voice": {
    "mode": "id",
    "id": "e07c00bc-4134-4eae-9ea4-1a55fb45746b"
  },
  "model_id": "sonic-2",
  // ...
}