Nicheloom visits: 59,847 all-time · 7,913 in the last 7 days

The opportunity tracker for new startups.

Today: 895 launches · Niche of the day: browser-based video games · See what launched today →

Minute

An Offline Meeting Notetaker Using Local LLMs

Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.

Want to reach these readers? Sponsor an issue.

HN · launched Nov 15, 2026 · 6 upvotes (top 66%) · 0 views

Niche: ai meeting note takers · 195 launches, 21 in the last 7 days ▼ -16% · Explore this niche →

Category and tags

  • Horizontal
  • Agent / copilot
  • Prosumer
  • AI-native
  • Commercial product

Visit website ↗ Source listing ↗

Could you build this?

Partial The UI and workflow are simple to vibe-code, and local Whisper plus a local LLM can be wired together. Reliable macOS system-audio capture and good offline speaker diarization are harder.

What it would actually take: Use a Swift/SwiftUI menu-bar app with ScreenCaptureKit for system audio and AVAudioEngine for the microphone. Run whisper.cpp for transcription and a GGUF model via llama.cpp or Ollama for summaries. Speaker labeling (e.g., pyannote-style diarization converted to CoreML) and call-app detection are the nontrivial parts, requiring some audio/ML engineering.

Discussion

1 comment analyzed.

Concerns raised: Unclear which transcription model is used, Unclear how audio recordings are stored, Site text mentions Whisper but screenshot shows Qwen, Gemma, Granite

Feature requests: Offload recordings after transcription to manage storage

Competitors

Other products that read as similar to this one : 1547 launches clear the similarity bar, closest 8 shown.

Attention rank: #982 of 1548 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).

Launched 381 days after the earliest competitor.

The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.