checklist.day

GPT Audio

JSON →
openai audio
audiotext

OpenAI's audio processing model for speech recognition and generation tasks.

Specs

context window 128K tokens
max output 16K tokens
input price $2.5 / 1M tokens
output price $10 / 1M tokens

Capabilities

streamingfunction-callingtool-use

Resources

homepageplatform.openai.com/docs/models/gpt-audio ↗
docsplatform.openai.com/docs/api-reference/audio ↗

API

full doc /v1/models/gpt-audio