Kokoro

request:
{"text": "Hello", "voice": "af", "speed": 1.0}

text: str = defaults to "Hi, I'm kokoro"
voice: str = defaults to "af", available options: "af", "af_bella", "af_sarah", "am_adam", "am_michael", "bf_emma", "bf_isabella", "bm_george", "bm_lewis", "af_nicole", "af_sky"
speed: float = defaults to 1.0. The speed of the audio generated

response:
{"base64": "base64 encoded bytestring"}

import httpx
import base64

# Replace the empty string with your model id below
model_id = ""
baseten_api_key = os.environ["BASETEN_API_KEY"]

with httpx.Client() as client:
    # Make the API request
    resp = client.post(
        f"https://model-{model_id}.api.baseten.co/production/predict",
        headers={"Authorization": f"Api-Key {API_KEY}"},
        json={"text": "Hello world", "voice": "af", "speed": 1.0},
        timeout=None,
    )

# Get the base64 encoded audio
response_data = resp.json()
audio_base64 = response_data["base64"]

# Decode the base64 string
audio_bytes = base64.b64decode(audio_base64)

# Write to a WAV file
with open("output.wav", "wb") as f:
    f.write(audio_bytes)

print("Audio saved to output.wav")

null