Realtime
  1. Server events
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
  1. Server events

session.updated

开发中
wss://api.openai.com/v1/realtime
Returned when a session is updated.

请求参数

Query 参数
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
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
Built with