Epilude

"About a second" for transcribe, punctuate, clean up, and tone match fully on-device is a strong latency claim for anything beyond basic speech-to-text. What's actually running locally and on what hardware, like is this Apple Silicon Neural Engine dependent, and what does the latency look like on older Intel Macs or lower-spec M1 machines versus a maxed-out M4?

Curious to see pricing evolve as features get added.

On-device cleanup in about a second is the impressive part — local transcription is mostly solved, but punctuation and tone-matching without a cloud round trip is where the latency usually hides. I build speech recognition into an unlock ritual, so I know the messy edges: half-finished sentences, restarts, the gap between what people say and what they meant to type. Curious how you handle a mid-sentence restart — does the cleanup pass merge it into one intent, or transcribe both fragments faithfully? Congrats on the launch.

Hey Product Hunt - Mark here, the other creator of Epilude.Our local dictation is second to none, we've spent a lot of time honing the models and process to get this running smoothly. I love knowing my voice or dictations aren't leaving my laptop - this is one for the privacy focused folk out there!I'd also watch this space if you're worried about sending your meetings to external servers - in August we will be launching our locally transcribed meeting notes. Watch this space!P.S. of course this was written with Epilude 😉

Awesome design! This is a total lifesaver for slow typists like me, and having everything processed fully on-device brings huge peace of mind.If you don't mind sharing, which local speech-to-text model (e.g., Whisper variant) are you running under the hood?

"trim the rambling" is the phrase that catches me, since that's not just punctuation cleanup, that's deciding what you didn't mean to say. for casual notes that's exactly what I'd want, but if I'm dictating something with a number, a caveat, or a qualifier in the middle of a rambly sentence, trimming risks cutting the part that mattered along with the filler. is there a way to see what got trimmed before it lands in the app, or does it commit straight to the final text with no diff to check against

Hey Product Hunt! I'm Gustav, one of the makers of Epilude.

Most of my work day is writing: prompting, code reviews, Slack messages and a lot of emails. When I hurt my elbow, I needed a to find a way to keep up my writing without putting too much strain on my arm, which led us to building Epilude.

We wanted a voice typing tool that was smooth as butter, typed what we intended to say just the way we intended to say it, and most importantly kept all our data on my Mac without anything we said being sent to anyone else's server.

Epilude is just that. It turns speech into finished writing, completely locally using open-weight speech-to-text and cleanup models that we've fine-tuned to work as well as possible on your Mac, with a tiny footprint.

After installing it (Mac only for now), simply hold a key, say what you want to write (even in a rough format), release. Epilude will transcribe, punctuate and format your writing, trim the rambling, and match the tone to the app you're in: formal in Mail, casual in iMessage. It takes about a second, and it works in any text field in your Mac.

My favourite use case is that I've noticed that it helps me code more effectively with LLMs. I've found rambling out a longer prompt and then tightening it up with Epilude is a lot faster and more effective than writing each prompt by hand. I type about 44 words a minute. I speak closer to 150.

Mac only for now, and Local Mode needs Apple Silicon. For now, full on-device cleanup requires 16GB of RAM whilst we optimise our local models; on smaller Macs you still get on-device transcription with basic formatting, and it still never touches the cloud.

If you've never used a voice dictation tool for Mac, I encourage you try dictating out your next long email or prompt!