Back to all models
openai
openaiOpenAI: 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.
openai/gpt-audio
Context Size
128K
Input Price
15,375 Ks/M
Output Price
61,500 Ks/M
Architecture
Text
Audio
Supported Parameters
frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetop_logprobstop_p
Details
TokenizerGPT
Max Completion16,384 tokens
Provider Context128K tokens
ModeratedYes