Model dossier

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...

ProviderOpenAI Start comparison

Context128,000

Max output16,384

Pricing viewTVP price

Identity

OpenAI: GPT Audio

Model ID: openai/gpt-audio
Canonical slug: openai/gpt-audio
Knowledge cutoff: n/a
Created: 1/19/2026

Capabilities

textaudiotoolsstructured

Modalities

text+audio->text+audiotextaudio

Capacity

Context128,000

Max output16,384

TokenizerGPT