session.created

开发中

wss://api.openai.com/v1/realtime

Returned when a session is created. Emitted automatically when a new connection is established.

请求参数

Query 参数

event_id

string

可选

The unique ID of the server event.

示例值:

event_1234

type

string

可选

The event type, must be "session.created".

示例值:

session.created

session

string

可选

object类型，以下皆为其中参数

string

可选

The unique ID of the session.

object

string

可选

The object type, must be "realtime.session".

model

string

可选

The default model used for this session.

modalities

array[string]

可选

The set of modalities the model can respond with.

示例值:

[""]

instructions

string

可选

The default system instructions.

voice

string

可选

The voice the model uses to respond - one of alloy, echo, or shimmer.

input_audio_format

string

可选

The format of input audio.

output_audio_format

string

可选

The format of output audio.

input_audio_transcription

string

可选

object类型，enabled、model都为其参数，Configuration for input audio transcription.

enabled

boolean

可选

Whether input audio transcription is enabled.

model1

string

可选

为model，The model used for transcription.

turn_detection

string

可选

object类型，type、threshold、prefix_padding_ms、silence_duration_ms都为其参数

type2

string

可选

The type of turn detection ("server_vad" or "none").

threshold

number

可选

Activation threshold for VAD.

prefix_padding_ms

integer

可选

Audio included before speech starts (in milliseconds).

silence_duration_ms

integer

可选

Duration of silence to detect speech stop (in milliseconds).

tools

array[string]

可选

Tools (functions) available to the model.

示例值:

["type","name","description","parameters"]

tool_choice

string

可选

How the model chooses tools.

temperature

number

可选

Sampling temperature.

max_output_tokens

integer

可选

Maximum number of output tokens.

Header 参数

Authorization

string

可选

示例值:

Bearer YOUR_API_KEY

OpenAI-Beta

string

可选

示例值:

realtime=v1

修改于 2024-10-14 23:56:45

conversation.item.created

session.updated