GPT-4o Audio is a general purpose, audio, realtime AI model developed by OpenAI, part of the GPT family. It was released on 2024-10-01. Its tracked lifecycle status is active. It supports a context window of 128,000 tokens.
Specifications
- Organization
- OpenAI
- Model family
- GPT
- Generation
- 4
- Status
- active
- Released
- 2024-10-01
- Model type
- General Purpose, Audio, Realtime
- Input modalities
- text, audio
- Output modalities
- text, audio
- Context window
- 128,000 tokens
- License
- Proprietary
- Weights
- closed weights
- Official API
- Yes
- Self-hostable
- No
- Last verified
- 2026-08-01
Capabilities
- Tool use
- Function calling
- Structured output
Related models in the GPT family
Interactive filtering and search on this page need JavaScript; every fact above is part of the page itself.