GPT Audio

Developer documentation

GPT Audio

GPT Audio for speech, transcription, translation, or voice generation workflows.

Model Reference

Audio and speech models

Text-to-speech, GPT audio chat, realtime sessions, transcription-oriented catalog rows, and voice settings. Endpoint: https://www.omixa.cloud/api/v1/audio

GPT Audio

gpt-audio

GPT Audio for speech, transcription, translation, or voice generation workflows.

Audio Context window: 128,000 tokens Max output: 16,384 tokens
input per 1m tokens $2.500000
output per 1m tokens $10.000000
minimum hold $0.010000
Integration reference

Connect GPT Audio

Use Omixa's unified endpoint and your workspace API key. Provider routing, billing, failover, and usage records are handled by Omixa.

POST https://www.omixa.cloud/api/v1/audio
  • Provider: azure-openai
  • Endpoint type: azure_openai_audio
  • Context window: 128,000 tokens
  • Max output: 16,384 tokens
Request schema

Request fields

Only send options supported by this model. Required fields and accepted values are listed below.

Field Type Required Accepted values Description
model string Yes gpt-audio Use `gpt-audio`. Omixa resolves the active provider route and failover key automatically.
task string No auto, tts, audio_chat, realtime, transcription, translation Audio workflow. Omixa maps it to speech, GPT audio chat, or realtime setup.
input string Yes Any valid value Text to speak, text prompt for audio chat, or realtime session instruction.
voice string No alloy, ash, ballad, coral, echo, sage, shimmer, verse, marin, cedar Voice name. Omixa maps common OpenAI voices to Google Gemini TTS voices when needed.
response_format string No mp3, wav, opus, flac, pcm16, aac Returned audio format.
speed number No 0.25-4 Speech speed for TTS routes.
instructions string No Any valid value Voice style or realtime/audio-chat behavior instructions.
Ready to send

Payload and response

Start with this model-safe payload and expect the normalized Omixa response shape shown beside it.

Example JSON payload
{
    "model": "gpt-audio",
    "task": "audio_chat",
    "input": "Create a short spoken answer explaining the benefits of one endpoint.",
    "voice": "alloy",
    "response_format": "mp3",
    "speed": 1
}
Response shape
{
    "object": "audio.speech|audio.chat|realtime.session",
    "data": {
        "content_type": "audio/mpeg",
        "audio_base64": "<base64-audio>"
    },
    "usage": {
        "estimated_audio_minutes": "0.100000"
    }
}
Language examples

Copy-ready integration code

Replace the example API key with a workspace key and keep model-specific fields unchanged unless the table above marks them optional.

cURL
curl -X POST https://www.omixa.cloud/api/v1/audio \
  -H "Authorization: Bearer omx_live_xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-audio",
    "task": "audio_chat",
    "input": "Create a short spoken answer explaining the benefits of one endpoint.",
    "voice": "alloy",
    "response_format": "mp3",
    "speed": 1
}'
JavaScript fetch
const response = await fetch('https://www.omixa.cloud/api/v1/audio', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer omx_live_xxx',
    'Content-Type': 'application/json'
  },
  body: "{\n    \"model\": \"gpt-audio\",\n    \"task\": \"audio_chat\",\n    \"input\": \"Create a short spoken answer explaining the benefits of one endpoint.\",\n    \"voice\": \"alloy\",\n    \"response_format\": \"mp3\",\n    \"speed\": 1\n}"
});
const data = await response.json();
Python requests
import requests

response = requests.post(
    'https://www.omixa.cloud/api/v1/audio',
    headers={'Authorization': 'Bearer omx_live_xxx', 'Content-Type': 'application/json'},
    json={
    "model": "gpt-audio",
    "task": "audio_chat",
    "input": "Create a short spoken answer explaining the benefits of one endpoint.",
    "voice": "alloy",
    "response_format": "mp3",
    "speed": 1
}
)
print(response.json())
PHP cURL
$ch = curl_init('https://www.omixa.cloud/api/v1/audio');
curl_setopt_array($ch, [
    CURLOPT_POST => true,
    CURLOPT_HTTPHEADER => ['Authorization: Bearer omx_live_xxx', 'Content-Type: application/json'],
    CURLOPT_POSTFIELDS => '{
    "model": "gpt-audio",
    "task": "audio_chat",
    "input": "Create a short spoken answer explaining the benefits of one endpoint.",
    "voice": "alloy",
    "response_format": "mp3",
    "speed": 1
}',
    CURLOPT_RETURNTRANSFER => true,
]);
$response = curl_exec($ch);
C# HttpClient
using var client = new HttpClient();
client.DefaultRequestHeaders.Authorization = new System.Net.Http.Headers.AuthenticationHeaderValue("Bearer", "omx_live_xxx");
var json = @"{
    ""model"": ""gpt-audio"",
    ""task"": ""audio_chat"",
    ""input"": ""Create a short spoken answer explaining the benefits of one endpoint."",
    ""voice"": ""alloy"",
    ""response_format"": ""mp3"",
    ""speed"": 1
}";
var response = await client.PostAsync("https://www.omixa.cloud/api/v1/audio", new StringContent(json, System.Text.Encoding.UTF8, "application/json"));
var body = await response.Content.ReadAsStringAsync();
Go net/http
payload := []byte(`{
    "model": "gpt-audio",
    "task": "audio_chat",
    "input": "Create a short spoken answer explaining the benefits of one endpoint.",
    "voice": "alloy",
    "response_format": "mp3",
    "speed": 1
}`)
req, _ := http.NewRequest("POST", "https://www.omixa.cloud/api/v1/audio", bytes.NewReader(payload))
req.Header.Set("Authorization", "Bearer omx_live_xxx")
req.Header.Set("Content-Type", "application/json")
resp, err := http.DefaultClient.Do(req)
Production checklist

Operational notes

  • Authenticate with `Authorization: Bearer omx_live_xxx`.
  • Omixa handles provider keys, routing, billing, failover, and usage recording behind this endpoint.
Copied Markdown