Speech generation model for controllable voice, narration, and audio delivery
Details
| Field | Value |
|---|---|
| id | openai/gpt-audio |
| family | gpt |
| modality | text+audio+pdf->text+audio |
| context_length | 128000 |
| max_output_tokens | 16384 |
| release_date | 2026-01-19 |
| is_open_weights | no |
| supports_tool_call | yes |
| supports_reasoning | no |
| supports_structured_output | yes |
| supports_attachment | yes |
| input_modalities | text, audio, pdf |
| output_modalities | text, audio |