GPT Audio
OpenAI🇺🇸
openai/gpt-audioGPT-Audio is OpenAI's model for natural speech input and output, generating expressive spoken responses directly from audio prompts. It is designed for voice assistants, spoken dialogue apps, and other audio-native interactions.
Taux de coût
2x
Contexte
128K
Date de sortie
19 janv. 2026
Entrée
TextAudio
Sortie
TextAudio
Prise en charge
RaisonnementAppel d'outilsSorties structurées