The app runs offline and lets you index local and external drives without needing to upload your content to the cloud. To use VEO you'll need an internet connection and your own API key.

We're only supporting Silicon Macs right now, but would consider Intel and Windows releases if there's interest. Price is $19.99 for a lifetime license that includes future updates.

If you have any feedback or want to join our discord, drop me a comment.

Demo: https://www.youtube.com/watch?v=fUUOd3TVBdY

Comments URL: https://news.ycombinator.com/item?id=45986392

Points: 1

# Comments: 0

Demo: https://www.youtube.com/watch?v=EVmRTNHV8o4

Comments URL: https://news.ycombinator.com/item?id=45971820

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=44963166

Points: 1

# Comments: 0

The semantic search queries typically take 100-250ms.

With your catalog indexed, you can use existing content to generate videos (text-to-video and image-to-video) using Veo 3. To try this out you'll need to bring your own Gemini API key. Obviously this part is not private since you are using Google's AI, but the generations get saved to your desktop and imo it's less clunky than the Google Videos UI. We also added a prompt pre-processing step to enrich the original user input. We use Gemini to create a structured JSON prompt that includes detailed information on lighting, audio, characters, and mood, to name it few. In my experience this makes it easier to preserve continuity in your scenes.

I want to experiment with some local generation models soon so Cosmos can function 100% offline (I've read good things about Wan 2.1 and Stable Diffusion). I really like working with local models (also using Whisper for audio to text transcription) and think long-term everyone will want at least some portion of their data managed by private, offline models.

If you are curious about building something like this for yourself, below is a rough outline: - Pick a platform or a cross-platform tool for your build (we started with Electron and eventually moved to Tauri) - Select your ML models. There are plenty of open-source image and text embedding models (Clip, Siglip, Nomic) - Design a media processing pipeline that won't fry your users' computer (pro tip: you're going to want to throttle indexing when CPU utilization gets too high) - Experiment with well-known open-source media tools like ImageMagick and FFmpeg. This is more than enough to extract frame, clip videos, or anything else you might want to do with a piece of media in your pre/post-processing - Database choice: There are lots of choices for DBs, but in my experience simpler is better. We started with Redis (it was overkill) and eventually migrated to sqlite with a vector embedding extension. Haven't tried Qdrant, Pinecone, or Chromadb, but sqlite works great for this use case. - If you want to support online AI platforms like OpenAI or Anthropic then you'll need to manage API keys and HTTP requests to these services (or maybe MCP? Don't know much about that yet).

Demo https://www.youtube.com/watch?v=qHPl_n-HlP4

Comments URL: https://news.ycombinator.com/item?id=44866633

Points: 16

# Comments: 8

Another use-case I have is recording my claude prompts as audio, transcribing them, and then pasting them into my terminal. I mostly work on the CLI (claude, ffmpeg, whisper), but I wanted to make a browser version.

Not reinventing the wheel here, just using Huggingface/Xenova Transformers.js to run Whisper in the browser with a background worker.

You can see a demo here: https://www.youtube.com/watch?v=ICLOvAq9vKE

If you're interested in building this yourself, there's a bunch of examples on Huggingface https://huggingface.co/collections/Xenova/transformersjs-dem...

Comments URL: https://news.ycombinator.com/item?id=44802063

Points: 26

# Comments: 10