Alt
A local AI lecture/meeting notetaker
Details
- External ID
- 46069536
- Source
- HN
- Company
- —
- Product
- Alt
- Website domain
- altalt.io
- Launched
- Nov. 27, 2025
- Cohort
- —
- Upvotes
- 5
- Upvotes percentile
- 0.0982532751091703
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
Most AI notetakers have a 300 minute limit. This is not enough for uni students like me, or people who do remote work.So, I made a notetaker that runs the ASR model on-device.- Free with local ASR & LLM models- No transcription time limit- High accuracy for non-english speech, support for 100 languages- Real-time transcription- Zoom/Google Meet support- No internet needed- Efficient battery usage (~6 hours on full charge on my M2 Pro)This started as a small cli tool I made for myself, then many of my uni friends really liked it, so here it is as an app!I hope a lot of people can use this in their classes or meetings to help with their work.During the development process, I also made the fastest streaming ASR pipeline on Apple Silicon. You can see it here: https://github.com/altalt-org/Lightning-SimulWhisper
Enrichment
- Theme
- AI voice recorders and meeting notetakers
- Vertical
- Horizontal
- Function
- Agent / copilot
- Audience
- B2C
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- local ai note taking for lectures and meetings
- Manually corrected
- False
Could you build this?
Partial Building a cross-platform desktop UI (Electron/Tauri) is straightforward, but packaging and optimizing local ASR (Whisper/CoreML), diarization, and on-device LLMs within strict PC memory and latency constraints requires specialized optimization.
What it would actually take: The app requires a native or Tauri frontend integrated with optimized local inference engines (like whisper.cpp, llama.cpp, or ONNX Runtime leveraging Apple Metal/CoreML and Windows DirectML). The hard parts are low-latency audio capture from system virtual devices, streaming speaker diarization (e.g., PyAnnote models adapted for local inference), and constrained memory orchestration so ASR and LLMs can run concurrently on consumer laptops. This requires native audio programming, model quantization, and embedded machine learning skills.
Discussion
1 comment analyzed.
Concerns raised: time limit
Competitors
Other products that read as similar to this one — 83 launches clear the similarity bar, closest 8 shown.
Attention rank: #81 of 84 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 20 days after the earliest competitor.
- VoiceCap · ph · 2026-09-19 · 100 upvotes · similarity 0.53
- threadfork · hn · 2026-07-21 · 10 upvotes · similarity 0.46
- On-device meeting transcription for your Mac · hn · 2026-03-18 · 6 upvotes · similarity 0.46
- I built a system for active note-taking in regular meetings like 1-1s · hn · 2025-12-08 · 177 upvotes · similarity 0.44
- Ellis · ph · 2026-07-07 · 186 upvotes · similarity 0.44
- A 4.8MB native iOS voice notes app built with SwiftUI · hn · 2026-01-27 · 7 upvotes · similarity 0.44
- Fellow for iOS · ph · 2026-04-16 · 189 upvotes · similarity 0.43
- VoiceTaking v2: The meeting note taker · ph · 2026-09-15 · 7 upvotes · similarity 0.42
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a agent / copilot tool for Agriculture yet.