Nicheloom visits: 58,137 all-time · 7,637 in the last 7 days

The opportunity tracker for new startups.

Today: 1,953 launches · Niche of the day: specialized calculation tools · See what launched today →

Muesli

If Granola and Wisprflow had an open source on device baby

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.

Hey folks, I am the developer behind muesli - which is your one stop app for all your speech to text needs, be it voice dictation or meeting transcriptions that runs on device on your Apple Neural Engine using CoreML based STT models (Parakeet, Whisper, Cohere transcribe). Everything is open source and we are at 160 stars - au naturale - would love for folks to use it and contribute further to the development

HN · launched May 4, 2026 · 15 upvotes (top 31%) · 0 views

Niche: voice dictation software · 224 launches, 16 in the last 7 days ▼ -30% · Explore this niche →

Category and tags
  • Horizontal
  • Workflow automation
  • Prosumer
  • AI-native
  • Hobby / open-source project

Visit website ↗ Source listing ↗

More like this: all 224 launches in voice dictation software →

Could you build this?

Partial Building a standard desktop UI for dictation is straightforward, but integrating local CoreML models with Apple Neural Engine (ANE) acceleration and low-latency audio capture pipelines requires platform-specific native systems work.

What it would actually take: The app needs a native macOS/Swift wrapper around AVFoundation for capturing system and microphone audio, coupled with CoreML STT runtimes (converting Whisper or Parakeet to CoreML with ANE-compatible tensor layers). The challenging parts are ensuring true zero-latency audio streaming, continuous VAD (voice activity detection), clipboard injection via Accessibility APIs, and optimizing CoreML execution so it stays entirely on the Neural Engine without thermal throttling.

Discussion

10 comments analyzed.

Competitors mentioned: Parakeet, Whisper, MSFT Vibevoice, IBM Granite

Concerns raised: On-device model accuracy vs cloud-hosted tradeoff, Model size and latency on consumer hardware

Feature requests: Store transcripts as markdown in file system, Add on-device CUA support, Support more speech models (Vibevoice, Granite)

Competitors

Other products that read as similar to this one : 83 launches clear the similarity bar, closest 8 shown.

Attention rank: #31 of 84 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).

Launched 187 days after the earliest competitor.

Related data

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.