Whisper Snapper for Mac

Whisper Snapper for Mac

Local transcripts with speaker labels, timestamps, + export

90 followers

Transcribe videos, podcasts, meetings, and voice memos with the fastest, most accurate AI models—running locally on your Mac or in the cloud with your own API keys. Speaker labels, timestamps, and export to SRT, Markdown, PDF, and more. Try free or one-time lifetime $9.99 Pro.
Whisper Snapper for Mac gallery image
Whisper Snapper for Mac gallery image
Whisper Snapper for Mac gallery image
Whisper Snapper for Mac gallery image
Whisper Snapper for Mac gallery image
Whisper Snapper for Mac gallery image
Free
Launch Team
Wispr Flow: Dictation That Works Everywhere
Wispr Flow: Dictation That Works Everywhere
Stop typing. Start speaking. 4x faster.
Promoted

What do you think? …

Evan Harris
Hey Product Hunt! 👋 I built Whisper Snapper because I wanted a transcription app that actually gave me control. Most tools force you into one camp: either fully cloud-based (privacy concerns, subscriptions) or fully local (slower, limited models). I wanted both. With Whisper Snapper, you choose: Go local with Parakeet or WhisperKit models—100% offline, your audio never leaves your Mac Go cloud with your own OpenAI or Deepgram API keys for speed and the latest models like GPT-4o It handles speaker diarization, exports to SRT/VTT for video editors, and works with any audio or video file you throw at it. The free tier is generous and permanent. Pro is a one-time $9.99—no subscriptions, ever. I'd love your feedback. What formats do you export to most? Any AI models you'd like to see added? Thanks for checking it out! 🎙️
Alex Cloudstar

Mostly export SRT + Markdown here. Love the pick local/cloud thing. Curious how fast Parakeet runs on an M1 Pro and if the fans stay chill. I’ll toss a 60‑min pod at it later. One‑time $9.99 feels right.

Evan Harris

@alexcloudstar Thanks! I think you'll be pleasantly surprised! I tested a 40 min podcast on the M1 and it handled it no-problem under 30 seconds with Parakeet.

Anton Loss

Nice and simple! Something that everyone needs!
Congrats on your launch! 🚀

Evan Harris

@avloss Thanks!

Paul Tseluyko

I love it's a native app!

Evan Harris

@pasha_tseluyko thanks! Native is important for full privacy!

Muhammad Farhan

Hey Evan @evan_harris5 ,


Congrats on the launch of Whisper Snapper! It seems like a great tool for transcribing with lots of flexibility in how it runs.


I’m curious, how’s the response been so far? What kind of marketing goals or strategies are you focusing on to get the word out? Would love to hear more about your plans!

Evan Harris

@mfarhan1107 thanks! Great response so far! It's a App Store app, so ASO and SEO are important!

Viktor Shumylo

Congrats on the launch! Love the flexibility of choosing between fully local and cloud transcription, that balance between privacy and speed feels very well thought out.

Yu Pan

This looks awesome! 🎉 Love the flexibility of choosing between local and cloud models—privacy and speed is a killer combo. Quick Q for the maker: How does Whisper Snapper handle background noise or low-quality audio? Does the local model (Parakeet/WhisperKit) perform well in those scenarios, or is cloud the better bet for messy recordings?

Also, any plans to add support for mobile (iOS/Android) in the future? Would love to transcribe on the go! 🚀

Evan Harris

@pany_ai Thanks! These models were trained on all kinds of audio, including lower-quality and in noisy environments. They seem to handle most everything I've thrown at it. I have noticed Deepgram in the cloud performs exceptionally well if the other models are having issues though. Nova2 has built-in noise optimization. This may be something I can add in for local models if needed though. An iOS app is definitely on the roadmap as well :)

Yu Pan

@evan_harris5 That’s great to hear — handling noisy, real-world audio is where these tools really prove their value. Nova2’s built-in noise optimization sounds especially powerful.
Excited to hear iOS is on the roadmap too! Curious whether you’re thinking about doing any on-device noise reduction or model switching automatically based on audio quality.

Yu Pan

@evan_harris5 That makes a lot of sense — having Deepgram as a cloud fallback when local models struggle sounds like a really pragmatic approach. Nova2’s noise optimization is a great baseline too.