Text to Speech

import requests

DEEPINFRA_TOKEN = "$DEEPINFRA_TOKEN"
MODEL = "hexgrad/Kokoro-82M"

response = requests.post(
    f"https://api.deepinfra.com/v1/inference/{MODEL}",
    headers={
        "Authorization": f"Bearer {DEEPINFRA_TOKEN}",
        "Content-Type": "application/json",
    },
    json={
        "text": "Hello! This is a text-to-speech example using DeepInfra.",
    },
)

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

curl -X POST \
  -H "Authorization: Bearer $DEEPINFRA_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello! This is a text-to-speech example using DeepInfra."}' \
  'https://api.deepinfra.com/v1/inference/hexgrad/Kokoro-82M' \
  --output output.wav