Voxta docs

FlashCap

Open-source camera / webcam capture library. Feeds webcam frames to vision-capable LLMs.

FlashCap is an open-source camera capture library. The Voxta module uses it to grab webcam frames and feed them to your active vision-capable LLM, so your character can see what your camera sees.

Marked experimental in the registry. Behavior and config may change.

Setup

Add the service

Manage Services → + Add Services → FlashCap → Add.

Pick a camera

In the config, choose your webcam from the device list. Multiple cameras can be defined and switched between.

Enable the Vision augmentation

Manage Services → + Add Services → Voxta Utilities: Vision → Add. This is what actually wires the captured frame into the chat prompt for a vision-capable LLM to interpret.

What the character sees

The character only sees frames when the Vision augmentation triggers — either on a user message that mentions the camera, or continuously if configured. They never see a live feed; just snapshots.

On this page