VoiceLiveModelFactory.SessionResponse Method
Definition
Important
Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.
The response resource.
public static Azure.AI.VoiceLive.SessionResponse SessionResponse(string id = default, string object = default, Azure.AI.VoiceLive.SessionResponseStatus? status = default, Azure.AI.VoiceLive.ResponseStatusDetails statusDetails = default, System.Collections.Generic.IEnumerable<Azure.AI.VoiceLive.SessionResponseItem> output = default, Azure.AI.VoiceLive.ResponseTokenStatistics usage = default, string conversationId = default, Azure.AI.VoiceLive.VoiceProvider voice = default, System.Collections.Generic.IEnumerable<Azure.AI.VoiceLive.InteractionModality> modalities = default, Azure.AI.VoiceLive.OutputAudioFormat? outputAudioFormat = default, float? temperature = default, Azure.AI.VoiceLive.MaxResponseOutputTokensOption maxOutputTokens = default);
static member SessionResponse : string * string * Nullable<Azure.AI.VoiceLive.SessionResponseStatus> * Azure.AI.VoiceLive.ResponseStatusDetails * seq<Azure.AI.VoiceLive.SessionResponseItem> * Azure.AI.VoiceLive.ResponseTokenStatistics * string * Azure.AI.VoiceLive.VoiceProvider * seq<Azure.AI.VoiceLive.InteractionModality> * Nullable<Azure.AI.VoiceLive.OutputAudioFormat> * Nullable<single> * Azure.AI.VoiceLive.MaxResponseOutputTokensOption -> Azure.AI.VoiceLive.SessionResponse
Public Shared Function SessionResponse (Optional id As String = Nothing, Optional object As String = Nothing, Optional status As Nullable(Of SessionResponseStatus) = Nothing, Optional statusDetails As ResponseStatusDetails = Nothing, Optional output As IEnumerable(Of SessionResponseItem) = Nothing, Optional usage As ResponseTokenStatistics = Nothing, Optional conversationId As String = Nothing, Optional voice As VoiceProvider = Nothing, Optional modalities As IEnumerable(Of InteractionModality) = Nothing, Optional outputAudioFormat As Nullable(Of OutputAudioFormat) = Nothing, Optional temperature As Nullable(Of Single) = Nothing, Optional maxOutputTokens As MaxResponseOutputTokensOption = Nothing) As SessionResponse
Parameters
- id
- String
The unique ID of the response.
- object
- String
The object type, must be realtime.response.
- status
- Nullable<SessionResponseStatus>
The final status of the response.
One of: completed, cancelled, failed, incomplete, or in_progress.
- statusDetails
- ResponseStatusDetails
Additional details about the status.
- output
- IEnumerable<SessionResponseItem>
The list of output items generated by the response.
- usage
- ResponseTokenStatistics
Usage statistics for the Response, this will correspond to billing. A VoiceLive API session will maintain a conversation context and append new Items to the Conversation, thus output from previous turns (text and audio tokens) will become the input for later turns.
- conversationId
- String
Which conversation the response is added to, determined by the conversation
field in the response.create event. If auto, the response will be added to
the default conversation and the value of conversation_id will be an id like
conv_1234. If none, the response will not be added to any conversation and
the value of conversation_id will be null. If responses are being triggered
by server VAD, the response will be added to the default conversation, thus
the conversation_id will be an id like conv_1234.
- voice
- VoiceProvider
supported voice identifiers and configurations.
- modalities
- IEnumerable<InteractionModality>
The set of modalities the model used to respond. If there are multiple modalities,
the model will pick one, for example if modalities is ["text", "audio"], the model
could be responding in either text or audio.
- outputAudioFormat
- Nullable<OutputAudioFormat>
The format of output audio. Options are pcm16, g711_ulaw, or g711_alaw.
Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.
- maxOutputTokens
- MaxResponseOutputTokensOption
Maximum number of output tokens for a single assistant response, inclusive of tool calls, that was used in this response.
Returns
A new SessionResponse instance for mocking.