# OpenAI: GPT Audio

Provider: openai  
Category: sound  
Model ID: `openai/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...

## Specs

- Context length: 128000 tokens
- Max output: 16384 tokens
- Modalities: text, audio
- Released: 2026-01-19

## Pricing

- Input: $2.50 per million tokens
- Output: $10.00 per million tokens

## Providers

- **openai** — ctx 128000, input $2.50/M, output $10.00/M

---
Last verified: 2026-04-23T23:46:29.618Z  
Canonical URL: https://switchy.build/models/gpt-audio