nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #333

You work at an organization that maintains a cloud-based communication platform that integrates conventional chat, voice, and video conferencing into one platform. The audio recordings are stored in…

The correct answer is B. Use the original audio sampling rate, and transcribe the audio by using the Speech-to-Text API. For audio recordings longer than one minute, Google recommends using the Speech-to-Text API's asynchronous recognition to handle longer processing times efficiently. Also, using the original 16 kHz sample rate preserves audio quality for better transcription accuracy…

Submitted by eva_at· Apr 18, 2026Data processing and feature engineering

Question

You work at an organization that maintains a cloud-based communication platform that integrates conventional chat, voice, and video conferencing into one platform. The audio recordings are stored in Cloud Storage. All recordings have a 16 kHz sample rate and are more than one minute long. You need to implement a new feature in the platform that will automatically transcribe voice call recordings into text for future applications, such as call summarization and sentiment analysis. How should you implement the voice call transcription feature while following Google- recommended practices?

Options

  • AUse the original audio sampling rate, and transcribe the audio by using the Speech-to-Text API
  • BUse the original audio sampling rate, and transcribe the audio by using the Speech-to-Text API
  • CDownsample the audio recordings to 8 kHz, and transcribe the audio by using the Speech-to-Text
  • DDownsample the audio recordings to 8 kHz, and transcribe the audio by using the Speech-to-Text

How the community answered

(41 responses)
  • A
    7% (3)
  • B
    85% (35)
  • C
    2% (1)
  • D
    5% (2)

Explanation

For audio recordings longer than one minute, Google recommends using the Speech-to-Text API's asynchronous recognition to handle longer processing times efficiently. Also, using the original 16 kHz sample rate preserves audio quality for better transcription accuracy. Synchronous recognition is intended for short audio clips and is not suitable for longer recordings.

Topics

#Speech-to-Text API#Audio sampling rate#Google Cloud best practices#Data preparation

Community Discussion

No community discussion yet for this question.

Sign up to join the discussion
Full PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice