AnythingLLM Default Transcription Model
️💡
Note:
Using the local whisper model on machines with limited RAM or CPU can stall AnythingLLM when processing media files. We recommend at least 2GB of RAM and upload files less than 10MB.
AnythingLLM ships with a built-in Transcription Model Xenova Whisper (opens in a new tab) which will automatically download on the first use.
