OpenAI Audio Chat App

Interact with GPT-4o audio model through text and audio inputs

Voice

Notes:

  • You must provide your OpenAI API key in the field above
  • The model used is gpt-4o-audio-preview for conversation, gpt-4o-transcribe for transcriptions, and whisper-1 for translations
  • Audio inputs should be in WAV format for chat and any supported format for translation
  • Available voices: alloy, ash, ballad, coral, echo, fable, onyx, nova, sage, shimmer, and verse
  • Each audio response is automatically transcribed for verification
  • The "Use Random Example Audio" button will load a random sample from OpenAI's demo voices
  • The translation feature supports 50+ languages, translating them to English
  • If you experience connection errors, the app will automatically retry up to 3 times