Google Cloud Speech-to-Text

Google Cloud Speech-to-Text converts audio into text using Google's speech-recognition models. The gRPC API is exposed through the google.cloud.speech.v1.Speech service, reached at speech.googleapis.com:443 over TLS, and the main method is Recognize for synchronous recognition.

Requests are built with TsgcGRPCSpeechRecognizeRequest, where Config sets Encoding, SampleRateHertz, LanguageCode and EnableAutomaticPunctuation, and Audio.Uri points to the audio. The reply is returned in TsgcGRPCSpeechRecognizeResponse, whose Results contain Alternatives with Transcript and Confidence.

The example below authenticates with a service-account JWT, wires a TsgcGRPCClient over a TsgcHTTP2Client to the Speech host, sets the authorization Bearer metadata and calls Recognize on a LINEAR16 16000 Hz en-US audio stored at a gs:// URI:

    oHTTP2 := TsgcHTTP2Client.Create(nil);
    oHTTP2.Host := 'speech.googleapis.com';
    oHTTP2.Port := 443;
    oHTTP2.TLS := True;

    oGRPC := TsgcGRPCClient.Create(nil);
    oGRPC.Client := oHTTP2;

    // service-account JWT authentication
    oGRPC.GoogleCloudOptions.JWT.KeyFile := 'service-account.json';
    oGRPC.GoogleCloudOptions.JWT.API_Endpoint := 'https://speech.googleapis.com/';
    oGRPC.DefaultMetadata.AddValue('authorization', 'Bearer ' + oGRPC.GoogleCloudOptions.JWT.Token);

    // build the typed request and call the method
    oRequest := TsgcGRPCSpeechRecognizeRequest.Create;
    try
      oRequest.Config.Encoding := 'LINEAR16';
      oRequest.Config.SampleRateHertz := 16000;
      oRequest.Config.LanguageCode := 'en-US';
      oRequest.Config.EnableAutomaticPunctuation := True;
      oRequest.Audio.Uri := 'gs://my-bucket/audio.wav';
      oResponse := oGRPC.Call('google.cloud.speech.v1.Speech', 'Recognize', oRequest.ToBytes);
      ShowMessage(oResponse.DataString);
    finally
      oRequest.Free;
    end;