Recipe Index

The ever-growing cookbook of examples shows common use-cases of the DeepTone SDK, pre- and post-processing strategies, visualisation ideas, and more. The recipes here are a great way to get familiar with the capabilities of DeepTone™.

Available SDK Recipes

1. 💡 Speech Detection
   1. basic analysis of audio files with built-in summarization options
   2. custom summarization options for audio file analysis
   3. custom speech threshold using the raw output of the model
2. 💡 Gender Model
   1. streaming from a microphone and reporting gender in real-time
   2. streaming from a microphone and reporting long monologues in real-time
3. 💡 Arousal Model
   1. basic analysis of audio files with built-in summarization options
   2. custom summarization options for audio file analysis
4. 💡 Emotions Model
   1. detect when speaker is tired
5. 💡 Language Model
   1. basic analysis of audio file with built-in summary
6. 💡 Speaker Detection
   1. quick visualisation of speaker transitions
   2. per speaker analysis, utilising additional models
   3. classic speaker separation - split a mono file into a stream for each speaker
   4. handle imperfect results
7. 💡 Underage Speaker Detection
   1. detect when speaker is a child
8. 💡 Audio Event Detection
   1. detect when a speaker is laughing
9. 💡 LUFS Model
   1. detect if an audio contains segments that are either too loud or too quiet