OpenAI: GPT Audio
Review
OpenAI's GPT Audio is a specialised audio-in/audio-out model from a trusted provider, but without published benchmark data and at a relatively high price point, its general business utility is difficult to quantify.
Assessment date: April 16, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
Performance Profile
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..
Capabilities
Architecture
| Modality | Text + Audio → Text + Audio |
| Tokenizer | GPT |
How does OpenAI: GPT Audio stack up?
Compare side-by-side with other emerging models.
Model Information
| OpenRouter ID |
openai/gpt-audio
|
| Provider | openai |
| Release Date | January 19, 2026 |
| Context Length | 128,000 tokens |
| Max Completion | 16,384 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $2.50 | $0.002500 |
| Output | $10.00 | $0.010000 |
