About GPT Audio
The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced at $32 per million input tokens and $64 per million output tokens.
Specifications
- Provider
- OpenAI
- Context Length
- 128,000 tokens
- Input Types
- text, audio
- Output Types
- text, audio
- Category
- GPT
- Added
- 1/19/2026