VoiceLiveSessionResponse Class
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.
Base for session configuration in the response.
public class VoiceLiveSessionResponse : System.ClientModel.Primitives.IJsonModel<Azure.AI.VoiceLive.VoiceLiveSessionResponse>, System.ClientModel.Primitives.IPersistableModel<Azure.AI.VoiceLive.VoiceLiveSessionResponse>type VoiceLiveSessionResponse = class
interface IJsonModel<VoiceLiveSessionResponse>
interface IPersistableModel<VoiceLiveSessionResponse>Public Class VoiceLiveSessionResponse
Implements IJsonModel(Of VoiceLiveSessionResponse), IPersistableModel(Of VoiceLiveSessionResponse)- Inheritance
-
VoiceLiveSessionResponse
- Implements
Constructors
| Name | Description |
|---|---|
| VoiceLiveSessionResponse() |
Initializes a new instance of VoiceLiveSessionResponse. |
Properties
| Name | Description |
|---|---|
| AllowParallelToolCalls |
Whether the model is allowed to call tools in parallel. |
| Animation |
The animation configuration for the session. |
| Avatar |
Configuration for avatar streaming and behavior during the session. |
| ExpiresOn |
Expiration time for the session. This value is set by the server and cannot be changed with |
| Id |
The unique identifier for the session. |
| Include |
List of include options for the session (e.g., logprobs, phrases, file search results). |
| InputAudioEchoCancellation |
Configuration for echo cancellation during server-side audio processing. |
| InputAudioFormat |
Input audio format. Default is 'pcm16'. |
| InputAudioNoiseReduction |
Configuration for input audio noise reduction. |
| InputAudioSamplingRate |
Input audio sampling rate in Hz. Available values:
|
| InputAudioTranscription |
Configuration for input audio transcription. |
| Instructions |
Optional instructions to guide the model's behavior throughout the session. |
| InterimResponse |
Configuration for interim response generation during latency or tool calls. To assign an object to this property use FromObjectAsJson<T>(T, JsonSerializerOptions). To assign an already formatted json string to this property use FromString(String). <remarks> Supported types: </remarks>Examples:
|
| MaxResponseOutputTokens |
Gets or sets the maximum number of tokens to generate in the response. |
| Metadata |
Set of up to 16 key-value pairs that can be attached to the session. This is useful for storing additional information about the session in a structured format, such as tracking IDs, user context, or application-specific labels. These key-value pairs are also included in Foundry resource logs for tracing and diagnostics. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long. |
| Modalities |
The modalities to be used in the session. |
| Model |
The model for the session. |
| OutputAudioFormat |
Output audio format. Default is 'pcm16'. |
| OutputAudioTimestampTypes |
Types of timestamps to include in audio response content. |
| ParallelToolCalls |
Whether the model is allowed to call tools in parallel. |
| ReasoningEffort |
Constrains effort on reasoning for reasoning models. Check model documentation for supported values for each model. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. |
| Temperature |
Controls the randomness of the model's output. Range: 0.0 to 1.0. Default is 0.7. |
| ToolChoice |
Gets or sets the tool choice strategy for response generation. |
| Tools |
Configuration for tools to be used during the session, if applicable. |
| TurnDetection |
Gets or sets the TurnDetection. |
| Voice |
Gets or sets the Voice. |
