OpenAI: gpt-audio API
OpenAI's flagship non-realtime audio model. It natively processes audio-to-audio with full prosody and emotional retention, optimized for high-fidelity 48kHz production, meeting summaries, and multilingual dubbing with enterprise-grade consistency.
- Context window: 128,000 tokens
- Max output: 16,384 tokens
- Input: text, audio
- Output: text, audio
- Tool calling: Supported
- Released: 2025-10-16
- Knowledge cutoff: 2025-09-30
Frequently Asked Questions
What is the context window of gpt-audio?
gpt-audio supports a context window of up to 128,000 tokens.
Does gpt-audio support function calling?
Yes. gpt-audio supports tool / function calling.
What is the knowledge cutoff of gpt-audio?
The knowledge cutoff of gpt-audio is 2025-09-30.