OpenAI Adds Audio Capabilities to Chat Completions and GPT-4o APIs

OpenAI has introduced audio input and output capabilities to its Chat Completions API. This new feature allows users to pass text or audio inputs and receive responses in text, audio, or both, making it ideal for asynchronous audio applications. Unlike the Realtime API, which is better suited for low-latency speech-to-speech interactions, the Chat Completions API is designed for multimodal applications that do not require real-time responses. The pricing for this new feature is noted to be relatively high. The GPT-4o API now also supports audio in and out. A live stream about this update is scheduled.