OpenAI: GPT Audio logo

OpenAI: GPT Audio

OpenAIllm

Published January 19, 2026

About

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.

Try OpenAI: GPT Audio

Test this model in the Sandbase Playground with your own prompts.

Open in Playground

Related Models