VoiceLiveModelFactory.AudioInputTranscriptionOptions 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.
Configuration for input audio transcription.
public static Azure.AI.VoiceLive.AudioInputTranscriptionOptions AudioInputTranscriptionOptions(Azure.AI.VoiceLive.AudioInputTranscriptionOptionsModel model = default, string language = default, System.Collections.Generic.IDictionary<string,string> customSpeech = default, System.Collections.Generic.IEnumerable<string> phraseList = default);static member AudioInputTranscriptionOptions : Azure.AI.VoiceLive.AudioInputTranscriptionOptionsModel * string * System.Collections.Generic.IDictionary<string, string> * seq<string> -> Azure.AI.VoiceLive.AudioInputTranscriptionOptionsPublic Shared Function AudioInputTranscriptionOptions (Optional model As AudioInputTranscriptionOptionsModel = Nothing, Optional language As String = Nothing, Optional customSpeech As IDictionary(Of String, String) = Nothing, Optional phraseList As IEnumerable(Of String) = Nothing) As AudioInputTranscriptionOptionsParameters
The transcription model to use. Supported values: 'whisper-1', 'gpt-4o-transcribe', 'gpt-4o-mini-transcribe', 'azure-speech'.
- language
- String
Optional language code in BCP-47 (e.g., 'en-US'), or ISO-639-1 (e.g., 'en'), or multi languages with auto detection, (e.g., 'en,zh').
- customSpeech
- IDictionary<String,String>
Optional configuration for custom speech models.
- phraseList
- IEnumerable<String>
Optional list of phrase hints to bias recognition.
Returns
A new AudioInputTranscriptionOptions instance for mocking.
