Your company retains many audio recordings of calls made to its customer call center in an on-premises database. Each recording is in WAV format and lasts approximately 5 minutes. You need to analyze the audio files for customer sentiment. You plan to use the Speech-to-Text API and want the most efficient approach. What should you do?
A
Upload the audio files to Cloud Storage2. Call the speech:longrunningrecognize API endpoint to generate transcriptions3. Call the predict method of an AutoML sentiment analysis model to analyze the transcriptions.
B
Upload the audio files to Cloud Storage.2. Call the speech:longrunningrecognize API endpoint to generate transcriptions3. Create a Cloud Function that calls the Natural Language API by using the analyzeSentiment method
C
Iterate over your local files in Python2. Use the Speech-to-Text Python library to create a speech.RecognitionAudio object, and set the content to the audio file data3. Call the speech:recognize API endpoint to generate transcriptions4. Call the predict method of an AutoML sentiment analysis model to analyze the transcriptions.
D
Iterate over your local files in Python2. Use the Speech-to-Text Python Library to create a speech.RecognitionAudio object and set the content to the audio file data3. Call the speech:longrunningrecognize API endpoint to generate transcriptions.4. Call the Natural Language API by using the analyzeSentiment method
Show Answer Answer Explanation Five-minute recordings require asynchronous speech:longrunningrecognize, because synchronous recognition is limited to audio of one minute or less. Storing the audio in Cloud Storage lets Speech-to-Text access it without repeatedly sending local file content. The Natural Language API's analyzeSentiment method is the prebuilt service for determining sentiment from the resulting transcription, so creating and invoking an AutoML sentiment model is unnecessary. A Cloud Function can automate that downstream analysis.
Learn more
Community Discussion