Text to Speech

Endpoint

POST https://api.agilecloud.ai/v1/audio/speech

Request Parameters

Send as application/json:

cURL Example

curl https://api.agilecloud.ai/v1/audio/speech \
  -H "Authorization: Bearer $DIRECTAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts",
    "input": "ACAI gives you AI inference with built-in compliance.",
    "voice": "alloy"
  }' \
  --output speech.mp3

Python SDK Example

from openai import OpenAI
from pathlib import Path

client = OpenAI(
    base_url="https://api.agilecloud.ai/v1",
    api_key="YOUR_API_KEY",
)

response = client.audio.speech.create(
    model="tts",
    voice="alloy",
    input="ACAI gives you AI inference with built-in compliance.",
)

Path("speech.mp3").write_bytes(response.content)

Models

Notes

• Response is streamed as raw audio bytes — pipe to a file or audio player.
• All 6 voices are available on both tts and tts-hd.
• Maximum input is 4,096 characters per request.
• Compliance guardrails (content safety, audit logging) apply to the input text.