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...
| Type | Model |
| Section | Models & platforms / text+audio->text+audio |
| Pricing | paid (от $2.5/mo) |
| Platform | Self-hosted |
| Systems | api, python, self-hosted |
| Hosting | cloud |
| Site language | en |
| Vendor | Openai |
| Launched | 2026-01-19 |