Text-to-Speech (TTS)

Convert text to natural-sounding speech audio.

Endpoint: POST /api/v1/audio/tts/generations
Auth: Required

Request Body

Field	Type	Required	Default	Description
input	string	Yes	—	Text to convert to speech
model	string	No	tts-1	TTS model ID
provider	string	No	openai	Provider name
voice	string	No	—	Voice selection
instructions	string	No	—	Voice control instructions
response_format	string	No	mp3	Audio format
speed	float	No	1.0	Speed (0.25–4.0)
additional_params	object	No	{}	Provider-specific parameters
byok_api_key	string	No	—	Your own provider API key

Available Voices (OpenAI)

alloy, echo, fable, onyx, nova, shimmer

Audio Formats

mp3, opus, aac, flac, wav, pcm

Examples

PythonJavaScriptcURL

import requests

response = requests.post(
    "https://api.indoxhub.com/api/v1/audio/tts/generations",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "openai/tts-1",
        "input": "Welcome to IndoxHub, the unified AI gateway.",
        "voice": "nova",
        "response_format": "mp3",
        "speed": 1.0
    }
)
result = response.json()
print(result["data"])

const response = await fetch("https://api.indoxhub.com/api/v1/audio/tts/generations", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "openai/tts-1",
    input: "Welcome to IndoxHub, the unified AI gateway.",
    voice: "nova",
    response_format: "mp3"
  })
});
const data = await response.json();
console.log(data.data);

curl https://api.indoxhub.com/api/v1/audio/tts/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/tts-1",
    "input": "Welcome to IndoxHub, the unified AI gateway.",
    "voice": "nova",
    "response_format": "mp3"
  }'

Response

{
  "request_id": "550e8400-e29b-41d4-a716-446655440000",
  "created_at": "2026-04-07T12:00:00Z",
  "duration_ms": 2100.0,
  "provider": "openai",
  "model": "tts-1",
  "success": true,
  "message": "",
  "data": { "audio_url": "..." },
  "usage": {
    "tokens_prompt": 0,
    "tokens_completion": 0,
    "tokens_total": 0,
    "cost": 0.015,
    "latency": 2100.0
  }
}