Mark by AirtopMeet Mark. Vibe automation for marketers.
Lispr is a free voice dictation and translation app for Mac and Windows. Hold a key, speak, release. Your words land in whatever app your cursor is in. Speak in ~99 languages and switch mid-sentence. Hold your translation key as well, and the translation lands instead, in any of 32 languages. Median latency 346 ms. The mic is off until you hold the key, and we never store your audio. No account, no model download, free.
Lispr
Hey Product Hunt! CTO here. I wrote most of Lispr's code, so I'll take the technical questions today.
The problem that started this: every dictation flow we tried did the same thing. Record a file, upload it, wait for the transcript. That round trip takes 1.5 to 2.5 seconds, and at that speed you stop trusting the tool and go back to typing.
So we built Lispr around one idea: the network work should happen while you speak, not after. The moment you press the key, we pre-warm the TLS connection. While you talk, audio is compressed to Opus and streamed out in 20 ms packets. By the time you release the key, most of the work is already done. Median latency in production is 346 ms across tens of thousands of dictations. That's the difference between "waiting for a tool" and "it just types."
The app itself is native Swift and AppKit. 3.67 MB, universal binary, runs on macOS 11+, including old Intel Macs. No 2 to 3 GB model download before first use.
The line we will not cross: no account, no transcript logging, and nothing trains a model unless you explicitly opt in. Our relay doesn't store your audio. We built it this way because we dictate our own emails, docs, and code comments through it all day.
Pro tip: nothing types while you speak, and nothing gets sent for you. Text lands at your cursor when you release the key, so in a chat it sits in the input field until you press Enter yourself. Don't like how it came out? Delete it and say it again. And if you hold your translation key as well, what lands is the translation instead, in any of 32 languages.
I'll be in the comments all day. Tell me where it breaks, which app it misbehaves in, and how it runs on your Windows machine. Honest technical feedback is the most useful thing you can give us today.
@myroslav_budzanivskyi Since Lispr relies on a cloud-based pipeline to achieve its ~350ms latency, what technical guarantees such as independent audits or ephemeral processing can you provide to ensure that my audio or transcripts are truly not being logged or used by your ASR providers, especially when I am not in a 'zero data retention' mode?
Lispr
@makimum_dev Fair question, and I'll answer it in two layers, because the honest answer has two layers.
What I can guarantee, because we wrote the code: our relay is stateless. It forwards audio and returns text. It has no storage attached, and no transcript content appears in our logs. There's no account, so there's nothing to attach a profile to. You can watch the traffic yourself: one request out while the key is held, one response back.
What depends on our speech provider: their published policy is retention of audio for up to 30 days for abuse review, then deletion. It is not used for training. That's a policy commitment from a company with enterprise customers, not a cryptographic guarantee, and I won't pretend otherwise.
On independent audits: we don't have one. We're a small team a few months in, and a real audit costs real money. It's on the roadmap along with per-device attestation. If you need audited zero-retention today, an on-device tool is the right call for you, and I mean that without irony. The trade you make there is a 2 to 3 GB model download and slower output.
Nothing trains a model unless you flip an explicit opt-in, and that opt-in is off by default.
Lispr
I do marketing for Lispr. But I'm writing this as its heaviest user, because the tool changed how I work before it ever became my job to talk about it.
The biggest surprise was my AI workflow. When I typed prompts, I kept them short and got generic answers back. Speaking, I give the model two minutes of context, examples, and constraints without thinking about my fingers, and the answers improved to the point where colleagues asked what I changed.
The second thing: I live in Poland and run my life in three languages. Ukrainian with family, English at work, Polish everywhere else. Switching the output language is one extra key held at release, so I think in Ukrainian and the message lands in English. Of everything in the app this is what I'd pay for.
Ask me anything about how we use it day to day. The founders are in this thread too.
I've been using Lispr on my mac almost every day, and it's honestly become one of those apps I keep coming back to. I work in marketing and also do mentoring, so I spend a huge chunk of my day writing feedback, docs, slack messages, briefs etc. It doesn't magically write everything for me, but it cuts the time I spend writing by a lot. Funny enough, I used Lispr to write this review too 😄
If your job involves writing a lot, I'd definitely recommend giving it a try.
Lispr
@katrya_syrotynska A review dictated through the product it reviews. That's the best QA report we got today 😄 Thank you!
"It doesn't write everything for me, but it cuts the time" is exactly the bar we aim for. Lispr types what you say and stays out of the rest. Curious which part of your day it took over first: the Slack messages or the briefs?
@konstantin_karpushin1 definitely Slack first! I write a lot of feedback during the day, so that was an instant win. Briefs were next. At this point, if I know I'm about to write more than a sentence, I instinctively open Lispr 🙏
Lispr
@katrya_syrotynska "More than a sentence" is the threshold we hear from users again and again. Below it, typing wins. Above it, speaking does.
One tip for the feedback and briefs: add your clients' and product names in the Vocabulary section of settings. Lispr also learns new terms from your dictations once a day, but seeding the important names gets the spelling right from the first dictation. Thanks for being here today 🙏
@konstantin_karpushin1 Any plans for an iPhone app? 👀 the built-in iphone voice dictation just doesn't feel nearly as convenient
Hey, congrats on the launch!!
I hope this can be a free alternate for Wispr flow! I've signed up and started using this!
Lispr
@sushied Thank you, Sushruthi! Hope it earns that role for you. If anything feels off compared to Wispr Flow, tell me, that's exactly the feedback we want right now.
Congrats on the launch! I'm a QA engineer on a multinational team, and most of my day happens in English chats while English isn't my first language. This thing killed my "pause, look up a word,rephrase" loop: I say it the way I'd say it out loud, release the key, and a clean English sentence shows up. Also started dictating my Claude Code prompts and they got longer and way more useful than what I used to type. Voted, obviously.
Lispr
@anatoliy_kovalchuk Thanks Anatoliy! The "pause, look up a word, rephrase" loop is exactly the tax we wanted to remove, and hearing it from someone whose whole day runs in English chats means the tool does its job. The longer-prompts effect is real: speaking removes the friction, so the context finally makes it into the prompt. Enjoy, and keep the feedback coming.
Lispr
Launch day is closing, and I want to say thank you before it does. To everyone who voted, commented, asked the hard questions about privacy and architecture, reported a stubborn trigger key, and dictated their first message with Lispr today: you made this day what it was. The questions in this thread already changed our roadmap notes, and that's worth more than any badge.
Lispr stays free, the work continues tomorrow, and I read every reply here. If you installed it today, tell me in a week how it's holding up.
Lispr
@konstantin_karpushin1 Closing thought from the engineering side: I expected launch day to be about upvotes, but the best part turned out to be the questions. Trust boundaries, failure modes on a flaky link, where the vocabulary list lives, how auto-grow decides it's confident enough. You stress-tested our architecture decisions in public, and they held. A few answers from this thread are going straight into our docs, because if people here asked, users everywhere are wondering. Thanks for a launch day that felt like a design review.
Dograh
Myroslav and Nelli, congrats on Lispr. Switching languages mid sentence without breaking the flow is the kind of detail that actually sells a dictation app
Lispr
@a6kme1 Thank you, Abhishek! That one comes straight from how we work ourselves: half a sentence in Ukrainian, a product name in English, back again. Once you stop thinking about which language mode you're in, dictation starts feeling like typing.