Dictly
Jannik Jung · Writing · Voice & Language
Dictly is an on-device dictation app that turns speech into clean, formatted text for macOS, iOS, and iPadOS. Most voice-to-text apps ship your audio to a server. Dictly doesn't. Recognition, formatting, and analytics all run locally. Your words never leave your hardware. It fits people who dictate constantly and don't want a cloud service holding their transcripts.
About Dictly
What Is Dictly
Dictly is a speech-to-text app built around one idea: dictation should feel instant and stay private. It listens as you speak, streams the transcription in real time, and formats the result with rules you control. The app claims a first-word latency of roughly 100 ms on Apple silicon and a download under 5 MB. Small numbers. For a tool that does its own speech recognition, that's lean.
The part that separates it from cloud dictation services is where the work happens. Recognition, formatting, and even optional usage analytics run on the device itself. The site states that network usage is 0 bytes. So the app keeps working in airplane mode with the same speed. For anyone dictating client notes, medical drafts, or internal messages, that removes the usual worry about where a transcript ends up.
The main limits are platform and scope. Dictly is Apple-only. Android and Windows users are out of luck. It's also a dictation tool, not a full transcription suite, meaning it won't handle long meeting recordings or speaker labels the way dedicated transcription platforms do.
Getting Started
- Download Dictly from the App Store on your Mac, iPhone, or iPad. The app is free to install with a built-in purchase for Pro.
- Grant microphone and accessibility permissions when prompted so the app can capture speech and insert text into other apps.
- Press the Quick Capture shortcut (default Shift + Command + D, and configurable) to open the overlay and start speaking.
- Pick a Workflow and per-app Profile to control how the text gets formatted before it lands.
- Insert the result with Type-out, Paste, or Copy, and turn on Auto-Submit if you want it to fire off in chat or productivity apps.
Product Information
A quick look at Dictly's pricing, supported platforms, and performance.
Best for
The users, tasks, and scenarios where this tool fits best.
Users
- Writers and journalists who draft by voice and want their text formatted before it hits the page, with no cloud dependency
- Developers leaving code comments in VS Code and notes in other apps, since per-app Profiles adjust formatting automatically
- Privacy-conscious professionals in legal, health, or security roles who can't send audio to a third-party server
- Apple users who switch between a Mac and an iPhone and want the same dictation behavior on both
Tasks
- Drafting emails and messages hands-free, using filler removal and Markdown formatting while you talk
- Capturing quick notes, task lists, and ideas before they slip away, even without a signal
- Writing structured documents with bullet lists or paragraphs shaped by a Workflow
- Working through a long writing session offline on a flight where cloud tools won't respond
Scenarios
- Dictating in a quiet office or at home and dropping the text straight into the app you're already using
- Taking notes during a commute with no connection, then syncing later
- Handling sensitive client or patient material where nothing can leave the device
- Speed-writing a first draft on a Mac where typing would break your focus
Key features
On-device transcription with a stable pipeline
Dictly is a voice-to-text app that performs speech recognition locally and streams the text as you speak. The site cites roughly 100 ms first-word latency on Apple silicon and a footprint under 5 MB. Everything runs on your hardware. So the app behaves the same online or in airplane mode. That matters when you're relying on it for off-the-grid work.
Workflows for formatting as you talk
A Workflow is a live pipeline that reshapes your words on the way in. You can chain stages, from removing filler words to applying Markdown, so the text leaves the app already structured. The pitch is consistency. A memo comes out as paragraphs. A checklist comes out as a list. You don't clean it up by hand afterward.
Per-App Profiles that switch formatting automatically
Profiles tie a Workflow to a specific app. Dictly applies the right one depending on where your cursor sits, so notes get bullet lists, Mail gets formatted paragraphs, and VS Code gets plain comments. This automatic switching is the feature that saves the most keystrokes in daily use.
Insertion modes and Auto-Submit
Once the text is ready, you choose how it lands: Type-out, Paste, or Copy. Auto-Submit goes a step further and sends the text for you, which is handy in chat and productivity apps where you'd otherwise hit Enter. Small detail. It adds up over a hundred dictations a day.
Custom dictionary for names and jargon
Recognition gets better when the app knows your vocabulary. The custom dictionary lets you add names, technical terms, and product codenames so they stop coming out garbled. Pro removes the cap on how many entries you can keep. Why does that matter? Because a misheard client name in a transcript costs you a round of edits.
Transcription history with search
The app keeps your past transcriptions and makes them searchable, so a note you dictated last week isn't lost. Full history access sits behind Pro, while the free tier keeps a lighter record plus a simple analytics view with trends and goals if you want to track how much you dictate.
Pros and cons
Pros
- Fully on-device processing means transcripts never touch a server, which is rare for dictation apps
- About 100 ms first-word latency keeps dictation feeling like speech rather than a wait
- Per-app Profiles handle formatting automatically, so text arrives ready instead of needing cleanup
- Sub-5 MB footprint and low memory use make it light even on older Apple hardware
- Works offline at the same speed, so a bad connection never interrupts a session
Cons
- Apple-only, with no Android or Windows version, which rules out mixed-device teams
- Free tier caps Workflows, dictionaries, and history, so heavy users will likely need Pro
- Built for dictation rather than long recordings, so it isn't a fit for transcribing meetings or interviews with speaker labels
Frequently asked questions
Dictly converts speech into formatted text on your Mac, iPhone, or iPad. You speak, and it produces cleaned-up text for messages, notes, documents, or code comments without sending anything to a server.
Related content
Explore related tools, skills, and articles for Dictly.
Dictly Alternatives
Emailwritr
Emailwritr · Writing · MarketingEmailwritr is an AI email copywriting tool built for affiliates, course creators, and online businesses that want more revenue from the list they already own. Instead of blank pages or generic chatbot prompts, this AI email writer generates welcome sequences, launch campaigns, cart recovery emails, and promo series from frameworks modeled on well-known direct-response copywriters. You connect your autoresponder, answer a few questions about your offer, and it writes the copy for you.
Swms
Swms AI · Writing · Productivity · BusinessSwms is an AI safety compliance tool that turns a plain description of a job into ready-to-use safety documents. Describe your project, trade, and known hazards, and it writes a safe work method statement, job hazard analysis, safe work procedure, RAMS, or safety data sheet in seconds. It also ships with Oscar, a chat assistant that answers workplace safety questions in any language. Teams in construction, mining, transport, and warehousing use it to cut the paperwork that usually eats into a workday.
Prosp
Prosp · Writing · Voice & Language · MarketingProsp is an AI LinkedIn outreach tool built for agencies and sales teams, and it writes the message and the voice note in your own voice for each prospect so they actually reply. You connect your accounts, find leads, and let the AI draft and send personalized messages at scale, all from one inbox. It's built for people running outbound at volume. That's the whole pitch. Every touchpoint still has to feel human.