VoiceLiveModelFactory.VoiceLiveSessionOptions 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.
Base for session configuration shared between request and response.
public static Azure.AI.VoiceLive.VoiceLiveSessionOptions VoiceLiveSessionOptions(string model = default, System.Collections.Generic.IEnumerable<Azure.AI.VoiceLive.InteractionModality> modalities = default, Azure.AI.VoiceLive.AnimationOptions animation = default, Azure.AI.VoiceLive.VoiceProvider voice = default, string instructions = default, int? inputAudioSamplingRate = default, Azure.AI.VoiceLive.InputAudioFormat? inputAudioFormat = default, Azure.AI.VoiceLive.OutputAudioFormat? outputAudioFormat = default, Azure.AI.VoiceLive.AudioNoiseReduction inputAudioNoiseReduction = default, Azure.AI.VoiceLive.AudioEchoCancellation inputAudioEchoCancellation = default, Azure.AI.VoiceLive.AvatarConfiguration avatar = default, Azure.AI.VoiceLive.AudioInputTranscriptionOptions inputAudioTranscription = default, System.Collections.Generic.IEnumerable<Azure.AI.VoiceLive.AudioTimestampType> outputAudioTimestampTypes = default, System.Collections.Generic.IEnumerable<Azure.AI.VoiceLive.VoiceLiveToolDefinition> tools = default, Azure.AI.VoiceLive.ToolChoiceOption toolChoice = default, float? temperature = default, Azure.AI.VoiceLive.MaxResponseOutputTokensOption maxResponseOutputTokens = default, BinaryData turnDetection = default);static member VoiceLiveSessionOptions : string * seq<Azure.AI.VoiceLive.InteractionModality> * Azure.AI.VoiceLive.AnimationOptions * Azure.AI.VoiceLive.VoiceProvider * string * Nullable<int> * Nullable<Azure.AI.VoiceLive.InputAudioFormat> * Nullable<Azure.AI.VoiceLive.OutputAudioFormat> * Azure.AI.VoiceLive.AudioNoiseReduction * Azure.AI.VoiceLive.AudioEchoCancellation * Azure.AI.VoiceLive.AvatarConfiguration * Azure.AI.VoiceLive.AudioInputTranscriptionOptions * seq<Azure.AI.VoiceLive.AudioTimestampType> * seq<Azure.AI.VoiceLive.VoiceLiveToolDefinition> * Azure.AI.VoiceLive.ToolChoiceOption * Nullable<single> * Azure.AI.VoiceLive.MaxResponseOutputTokensOption * BinaryData -> Azure.AI.VoiceLive.VoiceLiveSessionOptionsPublic Shared Function VoiceLiveSessionOptions (Optional model As String = Nothing, Optional modalities As IEnumerable(Of InteractionModality) = Nothing, Optional animation As AnimationOptions = Nothing, Optional voice As VoiceProvider = Nothing, Optional instructions As String = Nothing, Optional inputAudioSamplingRate As Nullable(Of Integer) = Nothing, Optional inputAudioFormat As Nullable(Of InputAudioFormat) = Nothing, Optional outputAudioFormat As Nullable(Of OutputAudioFormat) = Nothing, Optional inputAudioNoiseReduction As AudioNoiseReduction = Nothing, Optional inputAudioEchoCancellation As AudioEchoCancellation = Nothing, Optional avatar As AvatarConfiguration = Nothing, Optional inputAudioTranscription As AudioInputTranscriptionOptions = Nothing, Optional outputAudioTimestampTypes As IEnumerable(Of AudioTimestampType) = Nothing, Optional tools As IEnumerable(Of VoiceLiveToolDefinition) = Nothing, Optional toolChoice As ToolChoiceOption = Nothing, Optional temperature As Nullable(Of Single) = Nothing, Optional maxResponseOutputTokens As MaxResponseOutputTokensOption = Nothing, Optional turnDetection As BinaryData = Nothing) As VoiceLiveSessionOptionsParameters
- model
- String
The model for the session.
- modalities
- IEnumerable<InteractionModality>
The modalities to be used in the session.
- animation
- AnimationOptions
The animation configuration for the session.
- voice
- VoiceProvider
The voice configuration for the session.
- instructions
- String
Optional instructions to guide the model's behavior throughout the session.
Input audio sampling rate in Hz. Available values:
For pcm16: 8000, 16000, 24000
For g711_alaw/g711_ulaw: 8000
- inputAudioFormat
- Nullable<InputAudioFormat>
Input audio format. Default is 'pcm16'.
- outputAudioFormat
- Nullable<OutputAudioFormat>
Output audio format. Default is 'pcm16'.
- inputAudioNoiseReduction
- AudioNoiseReduction
Configuration for input audio noise reduction.
- inputAudioEchoCancellation
- AudioEchoCancellation
Configuration for echo cancellation during server-side audio processing.
- avatar
- AvatarConfiguration
Configuration for avatar streaming and behavior during the session.
- inputAudioTranscription
- AudioInputTranscriptionOptions
Configuration for input audio transcription.
- outputAudioTimestampTypes
- IEnumerable<AudioTimestampType>
Types of timestamps to include in audio response content.
Configuration for tools to be used during the session, if applicable.
- toolChoice
- ToolChoiceOption
Specifies which tools the model is allowed to call during the session.
Controls the randomness of the model's output. Range: 0.0 to 1.0. Default is 0.7.
- maxResponseOutputTokens
- MaxResponseOutputTokensOption
Maximum number of tokens to generate in the response. Default is unlimited.
- turnDetection
- BinaryData
Type of turn detection to use.
Returns
A new VoiceLiveSessionOptions instance for mocking.
