OpenAIEndpointWhisper
Wisej.AI.Endpoints.OpenAIEndpointWhisper
Namespace: Wisej.AI.Endpoints
Assembly: Wisej.AI (3.5.0.0)
Represents an endpoint for connecting to OpenAI's Whisper model for speech-to-text transcriptions.
public class OpenAIEndpointWhisper : SmartHttpEndpoint
This class is designed to interact with OpenAI's Whisper model, providing functionality to send audio data and receive transcriptions. It extends the SmartHttpEndpoint to leverage HTTP communication.
Constructors
OpenAIEndpointWhisper()

Initializes a new instance of the OpenAIEndpointWhisper class with default settings.
Sets the authentication method to "Bearer", the model to "whisper-1", and the response format to "text". The URL is set to OpenAI's audio transcription endpoint.
Properties
Model

String: Gets or sets the model used for transcription. (Default: "whisper-1"
)
URL

String: Gets or sets the URL for the OpenAI audio transcription endpoint. (Default: "https://api.openai.com/v1/audio/transcriptions"
)
Methods
AddMessages(payload, session, messages)

Adds user messages to the payload for the request.
Throws:
ArgumentNullException Thrown if any of the parameters are null.
CreateContent(data)

Creates the HTTP content for the request using the provided data.
Returns: HttpContent. A HttpContent object containing the request data.
ReadAssistantMessage(response, message)

Reads the assistant's message from the response and updates the message object.
Throws:
ArgumentNullException Thrown if any of the parameters are null.
ReadUsage(message, reply)

Reads the usage information from the reply. Not supported in this implementation.
Last updated