OpenAI: GPT Audio

Text input Audio input Text output Audio output
Author's Description

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...

Key Specifications
Cost
$$$$$
Context
128K
Released
Jan 19, 2026
Supported Parameters

This model supports the following parameters:

Max Tokens Frequency Penalty Temperature Tool Choice Logit Bias Top P Stop Seed Response Format Logprobs Tools Structured Outputs Presence Penalty Top Logprobs
Features

This model supports the following features:

Tools Response Format Structured Outputs
Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $2.5
Completion $10

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
OpenAI
OpenAI | openai/gpt-audio 128K $2.5 / 1M tokens $10 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by openai