gpt-audio
GPT Audio (OpenAI)
Yes — OpenAI deprecated GPT Audio on July 20, 2026 and shuts it down on January 20, 2027 (in 174 days). The recommended replacement is GPT Audio 1.5.
The GA audio model for Chat Completions, successor to the gpt-4o audio previews. Deprecated in July 2026 with a six-month runway, alongside the whole realtime and audio generation it belonged to.
The facts
| Provider | OpenAI |
|---|---|
| Model id | gpt-audio |
| Released | — |
| Deprecated | July 20, 2026 |
| Shutdown | January 20, 2027 · in 174 days |
| Status | Deprecated |
| Last verified | July 30, 2026 |
What to use instead
A point upgrade within the same family — the closest thing to a drop-in in the audio line.
What parameters gpt-audio-1.5 accepts on modelparams.dev
Change the id
In most cases the migration is one string. Check the parameter differences before you ship — newer models drop older sampling knobs more often than they add them.
- "model": "gpt-audio"
+ "model": "gpt-audio-1.5"
Frequently asked questions
- When will OpenAI GPT Audio shut down?
- OpenAI GPT Audio is scheduled to shut down on January 20, 2027, in 174 days.
- What replaces OpenAI GPT Audio?
- OpenAI recommends GPT Audio 1.5 (`gpt-audio-1.5`) as the replacement for OpenAI GPT Audio. A point upgrade within the same family — the closest thing to a drop-in in the audio line.
- Is OpenAI GPT Audio still available?
- Yes, for now. OpenAI GPT Audio is deprecated but still answers requests until January 20, 2027. Deprecated models get no further updates and are the first to lose capacity.
- How do I migrate from OpenAI GPT Audio to gpt-audio-1.5?
- Swap the model id in your API call: replace "gpt-audio" with "gpt-audio-1.5". A point upgrade within the same family — the closest thing to a drop-in in the audio line.
Sources
- OpenAI API deprecations · developers.openai.com · accessed July 30, 2026
Found something wrong? The data is one YAML file — edit it on GitHub.
This page, for machines
Drop the badge in a README so it turns red the day this model is retired:
[](https://modeldeprecations.dev/openai/gpt-audio)