Skip to main content

Usage guide

Setup, environment variables, and Python/JavaScript/Go usage examples.

​
OpenAIRealtime

Realtime speech-to-speech integration for the OpenAI Realtime API. Wraps an OpenAI Realtime model so it can be used as a full speech-to-speech provider within the runtime. Configuration is supplied through an OpenAIRealtimeConfig instance and resolved into a flat parameter map for the runtime.

​
Constructor

​
api_key
str | None
OpenAI API key. When omitted, the value of the OPENAI_API_KEY environment variable is used.
​
config
OpenAIRealtimeConfig | None
Provider configuration. When omitted, a default OpenAIRealtimeConfig is used.

​
aclose

Release any resources held by the integration. This implementation performs no work and exists so the integration can be used interchangeably with providers that require teardown.

​
cleanup

Clean up the integration by delegating to aclose.

​
OpenAIRealtimeConfig

​
Fields

​
model
str
default:"gpt-4o-realtime-preview"
​
voice
str
default:"alloy"
​
modalities
List[str]
default:"…"
​
temperature
float
default:"0.8"
​
max_response_output_tokens
Union[int, str]
default:"inf"
​
turn_detection
TurnDetectionConfig | None
default:"…"
​
input_audio_transcription
InputAudioTranscriptionConfig | None
default:"…"
​
tool_choice
str
default:"auto"