OpenAI: gpt-audio-mini API

A cost-efficient multimodal model designed for asynchronous audio-to-audio and text-to-audio tasks. It supports steerable voice characteristics (tone, emotion, pacing) and features high-fidelity 48kHz synthesis, bridging the gap between quality and affordability.

Frequently Asked Questions

What is the context window of gpt-audio-mini?

gpt-audio-mini supports a context window of up to 128,000 tokens.

What is the knowledge cutoff of gpt-audio-mini?

The knowledge cutoff of gpt-audio-mini is 2025-09-30.