Ghost Pepper 🌶️

The local-first approach resonates deeply. I built NexClip AI with the same philosophy — video stays on your Mac, only audio is sent for AI analysis when needed.The OCR context for disambiguation is clever. We solved a similar challenge with audio RMS data — using silence detection and sentence boundaries to create precise segment cuts instead of relying purely on transcript text.Curious: with the 2B Qwen model running locally, how much memory overhead are you seeing during a typical 60-min meeting transcription?

Your ‘smart cleanup’ is a key differentiator: how does the on-device cleanup/polish step work in practice (latency, prompt customization, failure modes like repetition/hallucination), and how do you decide when to clean aggressively vs keep a faithful transcript?

this is super refreshingeverything going cloud-first, while privacy is becoming a bigger concernfully local voice + transcription is a strong anglehow’s the performance compared to cloud models right now?

Ran into this building something with voice input. Had to drop cloud STT because of data policies at a couple companies I was demoing to. Local first completely changes that equation. Curious how your models handle technical vocab like camel case and library names? That's been one of the hardest parts for us.

This is the category I've been waiting for someone to take seriously. Every meeting-notes tool I've tried sends audio or transcripts to a cloud I don't control, and for anything under NDA that's a hard no. "100% local" being the headline (not a buried feature) tells me you understand the actual buyer. Question for the maker: what's the model running under the hood for the TTS side, and does it hold up on older Macs or is this an M-series-and-up product? Upvoted. Rooting for the local-first AI wave.

I think we can integrate the Gemma models also into this. One other thing is that I really want this for Windows too because right now I don't think we have any system which can work natively for Windows. Can you do that lab? That would be really helpful

I've always been a bit paranoid using cloud-based apps that collect super sensitive data. I expect more open-source, on-device apps like this will rise in popularity for that reason and the ability to modify to fit inside one's infra and workflows.

I built Ghost Pepper to be 100% private and run on local Huggingface models. I open-sourced it to get help from the community, little did I know Jesse Vincent, creator of Claude Superpowers would end up contributing more code than I (read: my Claude) did. I called it Ghost Pepper because all models run locally, no private data leaves your computer. And it's spicy to offer it open source.