Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

LocalScribe. Transcribe locally on Mac.

Talk is text. Record conversations, transcribe on-device.

Details

External ID
1244100
Source
PH
Company
—
Product
LocalScribe. Transcribe locally on Mac.
Website domain
producthunt.com
Launched
Sept. 8, 2026
Cohort
—
Upvotes
1
Upvotes percentile
0.30815693820825313
Tags
Productivity, Privacy, Menu Bar Apps
Fetched at
Sept. 8, 2026, 8:28 p.m.
Updated at
Sept. 8, 2026, 8:28 p.m.

Description

LocalScribe is a macOS app I built to capture conversations and turn them into text you keep. It records both sides (your mic and the other party), then transcribes and separates speakers on-device with Whisper or Parakeet. Apple silicon only: the models run locally and nothing leaves your Mac. Made for people who curate their own local knowledgebase. The transcript lands as plain text in a folder you pick. Telling people you're recording is your responsibility. No cloud. No subscription.

Enrichment

Theme
ai voice dictation and transcription tools
Vertical
Horizontal
Function
Content generation
Audience
B2C
AI stance
AI-native
Project type
Commercial product
Normalized one-liner
transcription software for mac users
Manually corrected
False

Could you build this?

Partial Building a basic macOS UI is vibe-codeable, but reliable system-level audio capture (CoreAudio / ScreenCaptureKit dual-channel routing) and bundling local whisper/parakeet diarization with CoreML optimizations requires non-trivial native system programming.

What it would actually take: The app requires Swift/macOS native development utilizing ScreenCaptureKit or virtual CoreAudio taps to capture two distinct audio channels (system output and microphone) without feedback. For inference, it relies on whisper.cpp or MLX/CoreML running locally on Apple Silicon, accompanied by an on-device speaker diarization pipeline (e.g., PyAnnote CoreML port). The primary hurdle is achieving robust virtual audio loopback permissions and low-latency on-device diarization on macOS.

Competitors

Other products that read as similar to this one — 308 launches clear the similarity bar, closest 8 shown.

Attention rank: #182 of 309 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 298 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a content generation tool for Government yet.