# `GenAI.Provider.OpenAI.Audio`
[🔗](https://github.com/noizu-labs-ml/genai/blob/main/lib/genai_providers/open_ai/audio.ex#L1)

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.

# `chat`

# `chat`

# `config_key`

Return config_key inference provide application config stored under :genai entry

# `default_encoder`

# `effective_settings`

Obtain map of effective settings: settings, model_settings, provider_settings, config_settings, etc.

# `endpoint`

Prepare endpoint and method to make inference call to

# `headers`

# `headers`

Prepare request headers

# `request_body`

Prepare request body to be passed to inference call.

# `run`

Build and run inference thread

# `standardize_model`

# `stream`

Build and run inference thread in streaming mode

---

*Consult [api-reference.md](api-reference.md) for complete listing*