Realtime
Server events
复制页面
Realtime
Realtime Websocket
Client events
session.update
input_audio_buffer.append
input_audio_buffer.commit
input_audio_buffer.clear
conversation.item.create
conversation.item.truncate
conversation.item.delete
response.create
response.cancel
Server events
error
conversation.item.input_audio_transcription.completed
conversation.item.input_audio_transcription.failed
conversation.item.truncated
conversation.item.deleted
input_audio_buffer.committed
input_audio_buffer.cleared
input_audio_buffer.speech_started
input_audio_buffer.speech_stopped
response.created
response.done
response.output_item.added
response.output_item.done
response.content_part.added
response.content_part.done
response.text.delta
response.text.done
response.audio_transcript.delta
response.audio_transcript.done
response.audio.delta
response.audio.done
response.function_call_arguments.delta
response.function_call_arguments.done
rate_limits.updated
conversation.created
conversation.item.created
session.created
session.updated
Server events
复制页面
session.updated
开发中
wss://api.openai.com/v1/realtime
Returned when a session is updated.
请求参数
Query 参数
生成代码
event_id
string
可选
The unique ID of the server event.
示例值:
event_5678
type
string
可选
The event type, must be "session.updated".
示例值:
session.updated
session
string
可选
object类型,以下皆为其中参数,The updated session resource.
id
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
生成代码
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
上一页
session.created