checklist.day

GPT-4o Transcribe

JSON →
openai audio
audiotext

A speech-to-text model in the GPT-4o family designed for high-accuracy audio transcription.

Specs

context window 16K tokens
max output 2K tokens
input price $2.5 / 1M tokens
output price $10 / 1M tokens

Capabilities

streaming

Dates

releasedMar 2025

Resources

homepageplatform.openai.com/docs/models/gpt-4o-transcribe ↗
docsplatform.openai.com/docs/api-reference/audio ↗

API

full doc /v1/models/gpt-4o-transcribe