GPT Audio 1.5
A text-to-speech model (OPENAI/GPT-AUDIO-1.5) available through the ImageGPT Audio (Text to Speech) API.
| Property | Value |
|---|---|
| Model ID | OPENAI/GPT-AUDIO-1.5 |
| Playground | Audio |
| Pricing | 50 credits per request |
Headers
Send your API key in the x-api-key header on every request. See
Authentication for details.
| Header | Required | Value |
|---|---|---|
x-api-key | Yes | YOUR_API_KEY |
Content-Type | Yes | application/json |
A missing or invalid key returns 401 Unauthorized.
Parameters
Request body fields for /generate/text-speech:
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | The text you want to convert to speech. |
model | string | Yes | — | Model ID to use. E.g. QWEN3/TTS-FLASH, ELEVENLABS/TTS, OPENAI/GPT-AUDIO-MINI. |
outputType | string | No | "binary" | Use "binary" to receive raw audio bytes, or "url" to get a hosted audio URL in JSON. |
voice | string | No | "alloy" | Voice name (applies to OpenAI and ElevenLabs models only). E.g. alloy, nova, rachel, josh. |
outputFormat | string | No | "mp3" | Audio format for the output (applies to OpenAI and ElevenLabs models only). Currently mp3. |
Request examples
- cURL
- JavaScript
- Python
curl -X POST https://api.imagegpt.online/generate/text-speech \
-H "Content-Type: application/json" \
-H "x-api-key: YOUR_API_KEY" \
-d '{"prompt":"ImageGPT is an AI platform to generate images, videos, audio, code, and chat responses using multiple advanced models in one place.","model":"OPENAI/GPT-AUDIO-1.5","outputType":"binary","voice":"alloy","outputFormat":"mp3"}'
fetch('https://api.imagegpt.online/generate/text-speech', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'x-api-key': 'YOUR_API_KEY'
},
body: JSON.stringify({
"prompt": "ImageGPT is an AI platform to generate images, videos, audio, code, and chat responses using multiple advanced models in one place.",
"model": "OPENAI/GPT-AUDIO-1.5",
"outputType": "binary",
"voice": "alloy",
"outputFormat": "mp3"
})
})
.then(res => res.blob())
.then(blob => {
const audio = new Audio(URL.createObjectURL(blob));
audio.play();
});
import requests
resp = requests.post(
"https://api.imagegpt.online/generate/text-speech",
headers={"x-api-key": "YOUR_API_KEY"},
json={
"prompt": "ImageGPT is an AI platform to generate images, videos, audio, code, and chat responses using multiple advanced models in one place.",
"model": "OPENAI/GPT-AUDIO-1.5",
"outputType": "binary",
"voice": "alloy",
"outputFormat": "mp3"
},
)
with open("speech.mp3", "wb") as f:
f.write(resp.content)
Response example
binary
Raw audio bytes (mp3 stream). Save directly to a file or create a Blob URL.
url
{
"success": true,
"url": "https://ai.imagegpt.online/imagegpt-pro-audio/1780682139387-amsq4xznzvi.wav",
"taskId": "imagegpt_qwen3/tts-flash-cu0zjaz1xlc1780682133698",
"duration": 1,
"creditsDeducted": 10
}
Pricing
50 credits per request.
Playground
Try this model live. Your key is used only in your browser to call the API directly and is never stored.
note
The browser playground calls https://api.imagegpt.online directly, so it only works if the API
allows cross-origin requests from this site. If it is blocked, use the cURL,
JavaScript, or Python samples above from your own server.