Text to Speech - WhollyAPI

Convert text to natural-sounding audio using TTS models.

WhollyAPI hosts text-to-speech models that convert text into natural-sounding audio. Browse all TTS models.

Endpoint

POST https://whollyapi.com/v1/inference/{model_name}

Example

import requests

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

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

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

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

Additional parameters

Each model may expose additional parameters such as voice selection, speed, and language. Check the model’s individual API documentation page for supported options.

Available models

Browse all text-to-speech models.