Audio Generation
Generate audio files from text transcripts using Google Text-to-Speech
Audio Generation Statistics
Overview of listening questions and audio generation status
Voice Configuration
Adjust the speaking rate for generated audio (0.25 = very slow, 1.0 = normal, 4.0 = very fast)
Speaking Rate: 0.85
Slower (0.25)
Normal (1.0)
Faster (2.0)
Generate Audio for Single Question
Enter a question ID to generate audio from its transcript
Question ID
Generate Audio
Batch Audio Generation
Generate audio for all listening questions that have transcripts but no audio (up to 50 questions)
This process may take several minutes depending on the number of questions. The system will generate audio for up to 50 questions at a time.
Generate Audio for All (0 questions)