Overview
GPT-Audio-1.5 is an OpenAI voice model for audio input and output through the Chat Completions API. It also supports text input and output, streaming, and function calling. (developers.openai.com)
Uses
It can power voice-enabled applications that accept recordings, answer questions about audio, or generate spoken responses from text or audio prompts. (developers.openai.com)
Limits
- Context window: 128,000 tokens; maximum output: 16,384 tokens.
- Knowledge cutoff: September 30, 2024.
- Image and video are not supported. Structured outputs, fine-tuning, and predicted outputs are not supported.
- API rate limits depend on usage tier; the free tier is not supported. (developers.openai.com)
Pricing
OpenAI API pricing, in USD per 1 million tokens, as listed on the official model page and checked November 16, 2026: (developers.openai.com)
| Token type | Input | Output |
|---|---|---|
| Text | $2.50 | $10.00 |
| Audio | $32.00 | $64.00 |
Cached-input or batch discounts for this model were not verified. Official model and pricing page.
Release and official sources
- Release date: February 23, 2026, when OpenAI announced its release to the Chat Completions API. (developers.openai.com)
- OpenAI API changelog
- Official model documentation and pricing
- Audio in Chat Completions guide