These models are for KoboldCpp's speech recognition. You would load them with `--whispermodel` or from the "Audio" tab in the GUI launcher.

![image/png](https://cdn-uploads.huggingface.co/production/uploads/63cd4b6d1c8a5d1d7d76a778/zPTgBos1StPjBHS51Rmj8.png)

Then in KoboldAI Lite, you can enable Voice Input in the settings (Push To Talk or Voice Detect)

![image/png](https://cdn-uploads.huggingface.co/production/uploads/63cd4b6d1c8a5d1d7d76a778/HuIbaoe5trKtnihCGpzaH.png)