LocalClicky
Control your Mac with your voice locally
Start new thread

LocalClicky can now see whats going in your videos and summarize using voice

by•

Just ask, "What's happening in sample.mp4?" or "Can you describe this video?" and it analyzes the content, identifies people, objects, actions, and scenes, then gives you a natural language summary. Simply mention the filename and it finds the video automatically. If it can't locate it, it asks you to pick the file. Once loaded, the video stays in context so you can keep asking follow up questions without reselecting it.

Watch it here:

26 views

Add a comment

Replies

Best

I notice users may rely heavily on automatic summaries. and I question whether this reduces their attention to actual video details and I also think about how different users might interpret the same summary in different ways over time.

 These summaries are sometimes very helpful for users that creates a lot of content everyday and just want to know a brief of what was the video actually shot for. I have seen a lot of creators having 100s of videos in their device struggling to keep up with which video have what internally

i really like the idea of asking about videos and getting spoken explanations and I feel this could change how people interact with media on daily basis usage.

Nice update! I like that the video stays in context after it's loaded.

Being able to ask follow-up questions without selecting the file again makes the whole experience feel much more natural.

I want to understand how LocalClicky indexes local video files and i wonder if it builds a temporary database or uses cloud processing for faster retrieval and privacy safety cocerns.

 Right now it's not indexing any data/media. I am building it in parallel and there's 0 cloud involvement and yeah latency is an issue but I know more distilled models will be soon coming up which will just remove that concern for these simple tasks

i wonder if this tool can handle privacy concerns when analyzing personal videos stored on local devices securely without upload.

 Right now its complete off the cloud so everything runs on local via ollama. Privacy concern is the only reason I built it