GPT Audio
Access GPT Audio through one API key. Audio-capable multimodal model.
OpenAI's audio-capable model. Processes audio input and generates text or audio output for multimodal applications.
No credit card required. Takes 30 seconds.
2,400+
Developers
1.2M+
API calls served
100+
Endpoints
$0.01
Per call
Yep, that's it.
Try it live
Send a message and see GPT Audio respond in real time.
Maximum tokens in the response.
Real-time tokens
Context Window
128K tokens
Max Output
16K tokens
Input Price
$3.50 / 1M tokens
Output Price
$14.00 / 1M tokens
Strengths
GPT Audio accepts audio input and can produce text or audio output, handling speech understanding within a single model.
It works across audio and text in one request, enabling voice-driven applications without separate transcription and synthesis steps.
Designed for voice assistants, conversational agents, and any product where spoken input or output is central.
A 128,000-token context window holds long conversations and transcripts alongside the audio it processes.
Quick start
Copy this snippet and start making calls with GPT Audio.
const res = await fetch('https://api.yepapi.com/v1/ai/chat', {
method: 'POST',
headers: {
'x-api-key': 'YOUR_API_KEY',
'Content-Type': 'application/json',
},
body: JSON.stringify({
"model": "openai/gpt-audio",
"messages": [
{
"role": "user",
"content": "Explain API gateways in 2 sentences."
}
],
"maxTokens": 256
}),
});
const { data } = await res.json();
console.log(data.message.content);Why use GPT Audio through YepAPI?
GPT Audio API: an audio-capable multimodal model
GPT Audio is OpenAI's audio-capable model, processing audio input and generating text or audio output for multimodal applications. It carries a 128K-token context window, and usage is billed at $3.50 per 1M input tokens and $14.00 per 1M output tokens covering its audio and text processing.
Through YepAPI you access GPT Audio with one OpenAI-compatible API key. That same key also reaches other models and YepAPI's SEO, SERP, and web-scraping endpoints, so a voice product can understand speech and pull live information from one account.
What is GPT Audio?
GPT Audio is OpenAI's audio-capable model, built to take audio as input and return text or audio as output within a single multimodal system. Instead of stitching together a separate speech-to-text engine, a language model, and a text-to-speech engine, it handles spoken understanding and generation directly, which simplifies voice-first applications. It carries a 128,000-token context window and up to 16,384 output tokens, so it can keep long conversations and transcripts in view. Usage is billed at $3.50 per 1M input tokens and $14.00 per 1M output tokens, covering the audio and text it processes.
Build with GPT Audio via YepAPI
Call the OpenAI-compatible /v1/ai/chat endpoint with your YepAPI key, passing audio alongside text in the message payload as the model's multimodal format allows. Because it follows the Chat Completions schema, you can integrate it from existing SDKs by changing the base URL and model name. Use it for voice assistants, spoken-Q&A features, and conversational agents that listen and reply. One key also covers other models plus SEO, SERP, and scraping APIs, so your voice app can fetch fresh web data while it talks.
GPT Audio API pricing — $3.50 / $14.00 per 1M tokens
GPT Audio is billed at $3.50 per 1M input tokens and $14.00 per 1M output tokens, with audio and text counted toward those token totals. Because spoken input and audio output consume tokens as the model processes them, costs scale with the length of the audio and conversation rather than a flat per-minute fee. Per-token billing means short voice exchanges remain inexpensive while you only pay for what is processed.
GPT Audio for voice-first assistants
The model is a natural fit for voice-first products: smart-assistant interfaces, spoken customer support, accessibility features, and any app where users speak and expect spoken or written replies. Handling audio and language in one model reduces pipeline complexity and latency versus chaining separate components, while the 128K context keeps a spoken conversation coherent over many turns. It is built for applications where voice is the primary interaction.
Try GPT Audio free
New YepAPI accounts include $5 in free credit with no card required. That lets you send real audio through GPT Audio and test its speech understanding and responses in your own voice application before committing.
Start generating in 30 seconds
$5 free credit on signup. No credit card required. Pay per call.
What developers say
“Switched from SerpAPI and cut our SERP costs by 80%. Same data quality, way simpler billing.”
“One API key for AI models, SERP data, and web scraping. Saved us from managing 4 separate providers.”
“The $5 free credit let us prototype our entire rank tracking feature before committing. No other API does that.”
Frequently asked questions
OpenAI's audio-capable model. Processes audio input and generates text or audio output for multimodal applications.
Input tokens cost $3.50 per 1M tokens and output tokens cost $14.00 per 1M tokens through YepAPI. No monthly minimums — you only pay for what you use.
Sign up for a free API key, then send requests to the /v1/ai/chat endpoint.
GPT Audio supports a 128K token context window with up to 16K output tokens per request.
Ready to use GPT Audio?
$5 free credit on signup. No credit card required. Pay per call.
Explore more models
GPT-4o Mini
OpenAIAccess GPT-4o Mini through one API key. Fast, cheap, and OpenAI-compatible.
GPT-4o
OpenAIAccess GPT-4o through one API key. Flagship reasoning and multimodal capabilities.
GPT-5.5
OpenAIAccess GPT-5.5 through one API key. OpenAI's newest and most capable model.