OpenAI
GPT Audio
Speech generation model for controllable voice, narration, and audio delivery
Model facts
- Context window
- 128K tokens
- Maximum output
- 16K tokens
- Cheapest paid input
- $2.5 per 1M tokens
- Cheapest paid output
- $10 per 1M tokens
- Open weights
- no
- Providers
- 2
Capabilities and modalities
tool calling, structured output, attachments, temperature control, text, audio, pdf.
Observed price history
- 2026-08-24: $2.5 input / $10 output per 1M tokens
API providers
- Kilo Gateway (OpenAI) — model id openai/gpt-audio; $2.5 input / $10 output per 1M tokens; provider documentation
- OpenRouter — model id openai/gpt-audio; $2.5 input / $10 output per 1M tokens; provider documentation