OpenAI/ GPT
GPT Audio
openai/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...
Released
2026-01-19
Context window
128K
Max output
16K
Weights
Closed
Modalities
Input
TextAudio
Output
TextAudio
Identity
- Version
- gpt-audio
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | openai/gpt-audio | openai_chat | 128K | 16K | TextAudio | TextAudio | Tool callStructuredTemperature | Moderated | input $2.5/M output $10/M | Yes |
| Kilo Gateway | openai/gpt-audio | openai_chat | 128K | 16K | TextAudio | TextAudio | Tool callStructuredTemperature | - | input $2.5/M output $10/M | Yes |
Capabilities
Tool callStructuredTemperature