SmartAudioWhisperAdapter

The listening half of the audio pair. Hand it an Audio control holding a recording and it returns the transcript, preserving the original language.

It is the foundation for voice notes, dictation and meeting capture inside a Wisej.NET application.

Transcription quality tracks the endpoint: use OpenAI's hosted Whisper, GroqCloud's accelerated version, or a LocalAI deployment when recordings must not leave the premises.

What it gives you

• Speech-to-text transcription via Whisper-class endpoints.
• Keeps the source language of the recording.
• Writes the result back to the control's Text property.

Use it for

• Voice notes in mobile-first Wisej.NET apps
• Meeting capture feeding summarised minutes
• Dictated form filling, paired with the data-entry adapter

Like every adapter, it runs through a SmartHub and inherits its SmartEndpoint — switching the model or provider never changes this code.

var hub = new SmartHub(this) {
    Endpoint = new OpenAIEndpointWhisper()
};

var whisper = new SmartAudioWhisperAdapter { Audio = audio1 };
string transcript = await whisper.TranscribeAsync();