Willow Voice
Voice dictation that actually works
Start new thread

Willow Scribe - Tell Scribe what to say. It writes the rest.

by•
Willow Scribe lets you speak the gist of what you want to say and writes the full message for you in your own voice. You talk the way you actually think and a finished message comes out the other side, ready to send. It works inside the apps where you already write the most like email, Slack, iMessage, and Google Docs. You can also highlight any text on your screen, tell Willow how to change it, and the selection gets rewritten in place. The more you use it, the more it sounds like you.

Add a comment

Replies

Best
Maker
đź“Ś
If you've ever used voice dictation for work, you know how quickly it gets difficult for real work communication and writing. You change your mind halfway through a sentence, and the transcriber types every word anyway. You go back to fix it, and sometimes you just give up and type the whole thing yourself. Typing gives you a moment to think before you put words on the page. But voice dictation expects you to think out loud in perfect sentences, which almost nobody can actually do. Scribe works differently. It feels more like talking to a smart writing assistant than dictating into a microphone. You give it the rough idea, the way you'd explain something to a friend, and it writes the actual message in your voice. You can ramble or change your mind and the message still comes out clean. The more you use it, the closer it gets to sounding like you. A few things Scribe does: 1. Writes a full message from a rough spoken idea. Hit your Scribe hotkey and say "write a follow-up to John about the design review" and Willow drafts the email in your voice. 2. Replies in context. Inside an email or Slack thread, say "reply and tell him I'll send the deck by Friday" and Scribe uses the existing thread to write the response. 3. Rewrites any text you highlight. Press your Scribe hotkey on a selection and say what you want changed. Try "make this writing more clear" or "rewrite this in Mandarin." 4. Works directly inside the apps you already write in, with full awareness of the document or thread around you. Close to 20% of ChatGPT usage is helping people with communication like drafting emails or rewriting messages. Scribe is built exactly for that job. It runs on your voice, lives inside the apps you're already using, and picks up your writing style. Willow now has two voice modes. Dictation, our original product, lets you type with your voice anywhere on your computer. And Scribe writes the message for you when you'd rather speak the gist. Between them, my hands have barely touched the keyboard today! For the Product Hunt community, we're offering 50% off for the first three months. Link at the top. Our team would like to hear your feedback. Try it for a few days, tell us what you'd want next, and we'll be in the thread answering questions all day.

The biggest issue for me has always been that I don’t speak in perfectly structured sentences, especially when writing emails, messages, or prompts. So the idea of turning a rough spoken thought into a clean message in your own voice feels much more useful than traditional dictation.

The context-aware replies are especially interesting. If it can understand the thread and draft something that actually fits the situation, that could save a lot of time. A few questions: how much does Willow learn from someone’s writing style over time, and can users control or reset that personalization? Also, how does pricing work after the Product Hunt discount?

Really curious to see where this goes. Good luck with the launch!

Maker

 Thanks so much for the thoughtful comment, really appreciate you digging into the details.

Yes, Willow does learn over time. It’s starting with the fundamentals like simple punctuation, word choice, and light phrasing. As you use it more, it gradually adapts to how you naturally respond, your tone, and the kinds of structures you prefer. The goal is for it to feel less like generic dictation and more like your voice, just cleaner and more structured.

You’re always in control of that personalization. You can reset or fine-tune it anytime by going to the Style Matching tab and adding your own specific habits or preferences, so it stays aligned with how you want to sound.

For pricing, the Product Hunt deal is 50% off for the first three months. That comes out to about $7.50 per month, or roughly $20 total for the three-month period.

Really appreciate the support and the great questions. Excited to see what you think once you’ve had a chance to try it!

honest question after 6 launches: what's the retention curve actually look like for scribe specifically versus the base dictation product. dictation has obvious daily utility because it replaces typing. scribe feels more like something people try for a week and then forget exists unless it's deeply in the habit loop. how are you solving for that

Maker

 Love the question. What we’ve actually seen with beta users is that Scribe ends up being stickier than traditional dictation!

On the surface, dictation feels like it has obvious daily utility because it replaces typing. But in practice, it’s a bit unnatural. You have to speak in a very specific, word for word way, almost like you’re talking to ChatGPT. That works in certain contexts, but it doesn’t map cleanly to how people naturally communicate in tools like email or Slack.

With Scribe, you just talk the way you normally would. It makes it much easier to adopt, because you’re not learning a new behavior. You’re just speaking naturally and letting it handle the formatting :)

Great work on this launch! Running inside the apps people already use instead of asking them to change their workflow is exactly the right call

Maker

 That’s exactly the biggest advantage of Willow. We live where you already work, inside the tools you use every day, so there’s nothing new to learn or switch to! We just fit into your existing workflow and make it better :)

The interesting bit here is the gap between “how I talk while thinking” and “how I want the final message to read.” A lot of voice tools preserve the first too literally, which makes the output fast but still not quite sendable.

I’d be curious how Willow separates transient spoken scaffolding — false starts, caveats, messy ordering — from durable voice traits like sentence rhythm, level of warmth, and how direct someone tends to be. That feels especially important inside Slack/email, where the same person may want a very different register depending on recipient and risk.

I've tried so many softwares for dictation but this is the best one I’ve ever used.

I’ve been a heavy user of Claude and GPT for a long time, especially for writing emails and posts. They’ve been a core part of my workflow.

Recently, I started using Willow Scribe (Ive used regular Willow dictation for about a year), and I absolutely love it. I’m using it to draft emails, create LinkedIn posts, refine prompts, and even support a white paper I’m currently writing. It feels much more natural and fluid, especially compared to traditional dictation tools that capture every false start and half-formed thought.

Willow has genuinely improved how I think and write in real time. I couldn’t recommend it more.

Maker

 Thank you so much for the incredibly thoughtful feedback, Jennifer. We’re thrilled it’s helping you think and write more fluidly in real time.

The "removes filler words" line is the actual unlock here — most dictation tools dump a raw transcript that still takes 30 seconds to clean up, which defeats the whole point.

Quick question: can I toggle the cleanup off for casual Slack messages where I want my real voice? Sometimes "um, actually" is the message.

Such a huge time-saver when trying to give personalized feedback to over 80 university students. It would have taken days if i had to type it all out.

Congrats on the launch!

12
Next
Last