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...
Specifications
- Provider
- OpenAI
- Type
- Vendor / proprietary
- Modality
- text+audio->text+audio
- Context window
- 128K
- Released
- January 19, 2026
Capabilities
Input: textInput: audioOutput: textOutput: audio
Strengths
frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_logprobstop_p
