GPT Audio

The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced at $32 per million input tokens and $64 per million output tokens.

ChatOpenAI128k tokens$2.7251 / $10.9006 · 1M

openai/gpt-audio

Context
128k tokens
Completion cap
16,384
Tools
Yes
JSON
Yes
Released
2026-01-19

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-audio",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is GPT Audio?
The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced at $32 per million input tokens and $64 per million output tokens. GPT Audio runs on the Geek Hub API (OpenAI-compatible). Model id: openai/gpt-audio.
Is GPT Audio free?
No. Input is $2.7251 per 1M tokens and output is $10.9006 per 1M tokens on Geek Hub (markup included).
What is the context length of GPT Audio?
GPT Audio has a 128k tokens context window. It supports up to 16,384 completion tokens.
Does GPT Audio support tool calling and structured outputs?
GPT Audio accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was GPT Audio released?
GPT Audio was released on 2026-01-19.

More models from OpenAI