OpenAI audio chat provider for spoken responses with current audio-capable models.
This provider uses POST /v1/chat/completions with gpt-audio-1.5 and
modalities: ["text", "audio"], so callers can generate speech from text or run a
bounded speech-to-speech turn through the shared GenAI.generate_media/2 media path.
For live, low-latency voice sessions, use OpenAI Realtime outside this sync media
contract.
Summary
Functions
Callback implementation for GenAI.InferenceProviderBehaviour.chat/7.
Return config_key inference provide application config stored under :genai entry
Obtain map of effective settings: settings, model_settings, provider_settings, config_settings, etc.
Prepare endpoint and method to make inference call to
Prepare request headers
Prepare request body to be passed to inference call.
Build and run inference thread
Callback implementation for GenAI.InferenceProviderBehaviour.standardize_model/1.
Build and run inference thread in streaming mode
Functions
Callback implementation for GenAI.InferenceProviderBehaviour.chat/7.
Return config_key inference provide application config stored under :genai entry
Obtain map of effective settings: settings, model_settings, provider_settings, config_settings, etc.
Prepare endpoint and method to make inference call to
Prepare request headers
Prepare request body to be passed to inference call.
Build and run inference thread
Callback implementation for GenAI.InferenceProviderBehaviour.standardize_model/1.
Build and run inference thread in streaming mode