Transcription OpenAI Delphi Client (3 / 5)

Transcription Delphi Example

OpenAI requires to build a request were you pass the audio file, the model, the temperature (to get a more ore less random output... find below a list of the available parameters.

- Filename: (Required) The audio file to transcribe, in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm.
- Model: (Required) ID of the model to use. Only whisper-1 is currently available.
- Prompt: An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.
- ResponseFormat: The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.
- Temperature: The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.
- Language: The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.

Find below a simple example transcribing an audio file using whisper-1

procedure DoFileTranscription(const aFilename: string);
var
  oRequest: TsgcOpenAIClass_Request_Transcription;
  oResponse: TsgcOpenAIClass_Response_Transcription;
begin
  oRequest := TsgcOpenAIClass_Request_Transcription.Create;
  Try
    oRequest.Filename := aFilename;
    oRequest.Model := 'whisper-1';
    oResponse := OpenAI.CreateTranscriptionFromFile(oRequest);
    Try
      DoLog(oResponse.Text);
    Finally
      oResponse.Free;
    End;
  Finally
    oRequest.Free;
  End;
end; 

Find below the compiled Demo for Windows using the sgcWebSockets OpenAI Delphi Library.