IBM Watson Speech to Text

from("file:/var/audio?noop=true")
  .to("ibm-watson-speech-to-text:mySTT?apiKey=RAW(yourApiKey)&operation=recognize&contentType=audio/wav")
  .process(exchange -> {
      String transcript = exchange.getMessage().getHeader(WatsonSpeechToTextConstants.TRANSCRIPT, String.class);
      System.out.println("Transcription: " + transcript);
  });

from("direct:start")
  .setHeader(WatsonSpeechToTextConstants.AUDIO_FILE, constant(new File("/path/to/audio.wav")))
  .setHeader(WatsonSpeechToTextConstants.TIMESTAMPS, constant(true))
  .to("ibm-watson-speech-to-text:mySTT?apiKey=RAW(yourApiKey)&operation=recognize")
  .process(exchange -> {
      SpeechRecognitionResults results = exchange.getMessage().getBody(SpeechRecognitionResults.class);
      results.getResults().forEach(result -> {
          result.getAlternatives().forEach(alt -> {
              alt.getTimestamps().forEach(timestamp -> {
                  System.out.println("Word: " + timestamp.getWord() +
                                   " - Start: " + timestamp.getStartTime() +
                                   " - End: " + timestamp.getEndTime());
              });
          });
      });
  });

from("direct:start")
  .setBody(constant(audioInputStream))
  .setHeader(WatsonSpeechToTextConstants.WORD_CONFIDENCE, constant(true))
  .setHeader(WatsonSpeechToTextConstants.CONTENT_TYPE, constant("audio/mp3"))
  .to("ibm-watson-speech-to-text:mySTT?apiKey=RAW(yourApiKey)&operation=recognize")
  .process(exchange -> {
      SpeechRecognitionResults results = exchange.getMessage().getBody(SpeechRecognitionResults.class);
      results.getResults().forEach(result -> {
          result.getAlternatives().forEach(alt -> {
              alt.getWordConfidence().forEach(wc -> {
                  System.out.println("Word: " + wc.getWord() +
                                   " - Confidence: " + wc.getConfidence());
              });
          });
      });
  });

from("direct:listModels")
  .to("ibm-watson-speech-to-text:mySTT?apiKey=RAW(yourApiKey)&operation=listModels")
  .process(exchange -> {
      List<SpeechModel> models = exchange.getMessage().getBody(List.class);
      models.forEach(model -> {
          System.out.println("Model: " + model.getName() +
                           " - Language: " + model.getLanguage() +
                           " - Description: " + model.getDescription());
      });
  });

from("direct:getModel")
  .setHeader(WatsonSpeechToTextConstants.MODEL_NAME, constant("en-US_BroadbandModel"))
  .to("ibm-watson-speech-to-text:mySTT?apiKey=RAW(yourApiKey)&operation=getModel")
  .process(exchange -> {
      SpeechModel model = exchange.getMessage().getBody(SpeechModel.class);
      System.out.println("Model details: " + model);
  });

from("file:/var/audio?include=.*\\.mp3")
  .to("ibm-watson-speech-to-text:mySTT?apiKey=RAW(yourApiKey)&operation=recognize&contentType=audio/mp3")
  .log("Transcript: ${header.CamelIBMWatsonSTTTranscript}");

// Transcribe Spanish audio
from("direct:spanish")
  .setBody(constant(spanishAudioFile))
  .setHeader(WatsonSpeechToTextConstants.MODEL, constant("es-ES_BroadbandModel"))
  .to("ibm-watson-speech-to-text:mySTT?apiKey=RAW(yourApiKey)&operation=recognize")
  .log("Spanish transcript: ${header.CamelIBMWatsonSTTTranscript}");

// Transcribe French audio
from("direct:french")
  .setBody(constant(frenchAudioFile))
  .to("ibm-watson-speech-to-text:mySTT?apiKey=RAW(yourApiKey)&operation=recognize&model=fr-FR_BroadbandModel")
  .log("French transcript: ${header.CamelIBMWatsonSTTTranscript}");

from("direct:speakers")
  .setHeader(WatsonSpeechToTextConstants.SPEAKER_LABELS, constant(true))
  .setHeader(WatsonSpeechToTextConstants.TIMESTAMPS, constant(true))
  .to("ibm-watson-speech-to-text:mySTT?apiKey=RAW(yourApiKey)&operation=recognize")
  .process(exchange -> {
      SpeechRecognitionResults results = exchange.getMessage().getBody(SpeechRecognitionResults.class);
      results.getSpeakerLabels().forEach(label -> {
          System.out.println("Speaker " + label.getSpeaker() +
                           " from " + label.getFrom() +
                           " to " + label.getTo() +
                           ": " + label.getFinal());
      });
  });

from("direct:customModel")
  .setHeader(WatsonSpeechToTextConstants.MODEL, constant("your-custom-model-guid"))
  .to("ibm-watson-speech-to-text:mySTT?apiKey=RAW(yourApiKey)&operation=recognize")
  .log("Custom model transcript: ${header.CamelIBMWatsonSTTTranscript}");

from("direct:listCustomModels")
  .to("ibm-watson-speech-to-text:mySTT?apiKey=RAW(yourApiKey)&operation=listCustomModels")
  .process(exchange -> {
      List<LanguageModel> models = exchange.getMessage().getBody(List.class);
      models.forEach(model -> {
          System.out.println("Custom Model: " + model.getCustomizationId() +
                           " - Name: " + model.getName() +
                           " - Language: " + model.getLanguage() +
                           " - Status: " + model.getStatus());
      });
  });

from("direct:getCustomModel")
  .setHeader(WatsonSpeechToTextConstants.MODEL_NAME, constant("your-custom-model-guid"))
  .to("ibm-watson-speech-to-text:mySTT?apiKey=RAW(yourApiKey)&operation=getCustomModel")
  .process(exchange -> {
      LanguageModel model = exchange.getMessage().getBody(LanguageModel.class);
      System.out.println("Custom model: " + model.getName() +
                       " - Status: " + model.getStatus() +
                       " - Progress: " + model.getProgress() + "%");
  });

from("direct:start")
  .setBody(constant(audioFile))
  .to("ibm-watson-speech-to-text:mySTT?apiKey=RAW(yourApiKey)&serviceUrl=https://api.eu-gb.speech-to-text.watson.cloud.ibm.com&operation=recognize")
  .log("Transcript: ${header.CamelIBMWatsonSTTTranscript}");

mvn verify \
  -Dcamel.ibm.watson.stt.apiKey=YOUR_API_KEY \
  -Dcamel.ibm.watson.stt.serviceUrl=YOUR_SERVICE_URL

export CAMEL_IBM_WATSON_STT_API_KEY=YOUR_API_KEY
export CAMEL_IBM_WATSON_STT_SERVICE_URL=YOUR_SERVICE_URL

mvn verify \
  -Dcamel.ibm.watson.stt.apiKey=${CAMEL_IBM_WATSON_STT_API_KEY} \
  -Dcamel.ibm.watson.stt.serviceUrl=${CAMEL_IBM_WATSON_STT_SERVICE_URL}

[INFO] Running org.apache.camel.component.ibm.watson.stt.integration.WatsonSpeechToTextIT
Created input directory: target/audio-input
Created output directory: target/transcription-output
Generated test audio file: target/audio-input/test-audio.wav
Successfully transcribed audio. Transcript: "Hello this is a test of IBM Watson Speech to Text"
Confidence: 0.98
Found 25 language models
  Model: en-US_BroadbandModel - Language: en-US - Rate: 16000
  Model: en-GB_BroadbandModel - Language: en-GB - Rate: 16000
Retrieved model details: en-US_BroadbandModel - Description: US English broadband model
Successfully transcribed with timestamps (5 words with timing information)
Successfully transcribed with word confidence (5 words with confidence scores)
Successfully saved transcript to file: target/transcription-output/transcript-basic.txt (size: 156 bytes)
Successfully saved transcript with timestamps to: target/transcription-output/transcript-with-timestamps.txt (size: 452 bytes)
Successfully saved detailed transcript to: target/transcription-output/transcript-detailed.txt (size: 678 bytes)
Created transcript file: transcript-file1.txt (size: 156 bytes)
Created transcript file: transcript-file2.txt (size: 156 bytes)
Created transcript file: transcript-file3.txt (size: 156 bytes)
Successfully transcribed and saved 3 audio files
[INFO] Tests run: 12, Failures: 0, Errors: 0, Skipped: 0