OpenAI
OpenAI: GPT Audio
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 at $32 per million input tokens and $64 per million output tokens.
Input
$2.5
/ 1M tokens
Output
$10
/ 1M tokens
Context window
128K
tokens
Limits
Context
128,000
tokens
Max output
16,384
13% of the context window
Model facts
Author
OpenAI
Tokenizer
GPT
Modality
Text + Audio -> Text + Audio
Created
Jan 19, 2026
Publication status
Hugging Face: unavailableLicense: not publishedParameter count: not published
Modalities
Input · TextInput · AudioOutput · TextOutput · Audio
Generation controls
Frequency penaltyLogit biasLogprobsMax tokensPresence penaltyResponse formatSeedStopStructured outputsTemperatureTool choiceToolsTop logprobsTop p