GPT Audio
All models
OpenAIOpenAIGPT Moderated

GPT Audio

128K context$2.50/M input$10.00/M output

GPT Audio is an AI model from OpenAI built for agent workflows, with support for text, audio input and text, audio output. 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...

What is GPT Audio?

GPT Audio is an AI model from OpenAI that Agent Mag tracks for pricing, context window, modalities, benchmarks, and API compatibility. Builders can use this page to compare GPT Audio against other models for agent workflows and production deployments.

Model ID

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...

Modalities
Input
textaudio
Output
textaudio
Supported Parameters
frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_logprobstop_p

Related content