Launching today
Epilude
Local voice dictation for Mac for polished text
67 followers
Local voice dictation for Mac for polished text
67 followers
Hold a key, speak, release: polished text lands in any app on your Mac. Epilude transcribes, punctuates, cleans up, and matches your tone in about a second. Runs fully on-device, so audio never leaves your Mac.
Epilude
"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
Epilude
@galdayan Great question - straight answer: there's no diff before the text lands, it commits straight in.
However every dictation is saved to your local history with the raw transcript kept next to the cleaned one, plus a "See what changed" word-level diff for exactly this, so you can always check and copy the raw back.
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?
Epilude
@zeo81 Thanks! Privacy is the whole reason we are building Epilude, so this is great to hear.
It's actually not Whisper. On-device you're running Epilude Model 4: a state-of-the-art open speech model we've optimised for Apple Silicon, paired with our own cleanup model (a fine-tune on the Qwen family) that turns the raw transcript into something you'd actually send. Full attributions are in the app under Acknowledgements.
If you want the full nerdy breakdown, including how we grade every model against a zero-tolerance error bar before it ships, we wrote it up here: https://epilude.com/news/introducing-model-4
@mark_mason6 Thanks for the reply! I thought you were using Whisper like everyone else — turns out it's your own tech, which is seriously impressive. Huge kudos to you guys, haha. Wishing you great rankings on Product Hunt!
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.
"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?
Epilude
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 😉
Curious to see pricing evolve as features get added.