AI dictation apps have come a long way in a short period of time. For years they were slow and imprecise unless they spoke with a certain intonation and pronounced clearly.
Advances in large language models (LLMs) and speech-to-text models have changed this situation, creating systems that can more accurately decode speech while retaining enough context to properly format text. Developers also have built-in features to automatically remove filler words, correct misspellings, and handle punctuation, outputting text that requires far less editing.
There are dozens of these apps on the market today, so we’ve rounded up some of the best and most useful dictation apps available today.
Wispr flow
Wispr Flow is a well-funded AI dictation app that allows you to add custom words and instructions for your dictation. There are native apps for macOS, Windows, and iOS. An Android version is in the works.
The app lets you customize how you transcribe text by choosing between “Formal,” “Casual,” and “Ultra Casual” styles for different types of writing, including personal messages, work, and emails. And when used with Vibe coding tools like Cursor, you can turn on automatic recognition of variables or tag files in chat.
This app lets you copy text for free, up to 2,000 words per week on desktop and 1,000 words per month on iOS. Paid subscription plans offer unlimited transcription and start at $15 per month.
willow
Willow advertises itself as a huge time saver for people who don’t like typing. Along with the usual features like automatic editing and formatting, the app uses a large-scale language model to generate entire passages of text from just a few dictated words.
Willow also takes a more privacy-focused approach by storing all history locally on your device, and allows you to opt out of model training entirely. You can also add custom vocabulary to help you adapt to industry terms or local dialects.
Willow lets you dictate 2,000 words a month for free on its desktop app. Personal subscription plans start at $15 per month and unlock unlimited dictation and allow the app to remember your writing style.
monologue
If privacy is your top priority, Monologue allows you to download and record AI models directly to your device, with your data fully protected in the cloud. Plus, the app lets you customize the tones depending on the app you use.
With Monologue, you can transcribe 1,000 words per month for free. Subscription costs $10 per month or $100 per year. The company also sends its most active users a physical shortcut device called a Monokey to use with the app.
Super Whisper
Superwhisper is primarily a dictation app, but it can also copy text from audio or video files. The app lets you select and download AI models, including Nvidia’s Parakeet speech recognition model, along with several of our own AI models at different speeds and accuracy levels.
The app also lets you write custom prompts to adjust output and lets you view both processed and unprocessed content directly from the system keyboard.
Basic speech-to-text features are available for free, and you can test out Pro features like translation and transcription for 15 minutes. The paid tier allows you to use your own AI API keys and connect cloud and local models with no usage limits.
The monthly plan costs $8.49 per month, the annual plan costs $84.99 per month, and you can pay $249.99 per month for a lifetime subscription.
VoiceTypr
The VoiceTypr app takes an offline-first, non-subscription approach, allowing you to use a local model for transcription. There is also a GitHub repository for those who want to host and run the open source version themselves. VoiceTypr supports over 99 languages and works on both Mac and Windows.
You can try the app for free for 3 days, after which you can purchase a lifetime license. The app costs $35 for one device, $56 for two devices, and $98 for four devices.
aqua
Aqua is a Y Combinator-backed voice typing app for Windows and macOS that claims to be one of the fastest tools in its category in terms of latency (the delay between when you speak and when the text appears on the screen).
In addition to handling grammar and punctuation, Aqua can also auto-fill text by speaking phrases. For example, you can say “my address” and Aqua will fill it out for you.
The app also provides its own speech-to-text API, allowing other apps to connect to Aqua’s transcription engine.
The free tier comes with 1,000 words per month. Paid plans start at $8 per month per year and unlock unlimited words and 800 custom dictionary values.
handy
Handy is an open-source, free transcription tool that runs on Mac, Windows, and Linux. The app is very basic and doesn’t offer much customization, but it’s a good choice if you want to use your voice more and don’t want to pay for it.
The app has a preferences menu where you can toggle Push to Talk and change shortcuts to enable transcription.
Informal
Typeless stands out for its high number of free words. The company claims that it does not retain any data or use it to train AI models. Typeless also gives you the ability to rewrite sentences where you made a mistake.
The app lets you dictate up to 4,000 words per week (about 16,000 words per month) on the free tier. Pay $12 per month (billed annually) to unlock unlimited words and access new features. Typeless is only available on Windows and macOS.
voice ink
VoiceInk is an open source personal dictation app for Mac. The app supports global shortcuts to start/stop recording along with push-to-talk mode. Reads the context of the screen and adjusts the output accordingly.
The app can automatically detect specific apps and URLs and apply custom formats or rules to each. We also have an assist mode to answer your questions. Lifetime access to the app costs $25 for one device, $39 for two devices, and $49 for three devices.
dictation
Dictato is a dictionary app for Mac that sells for 9.99 euros (about $12) and offers lifetime access and two years of feature updates. The app works with offline models like Parakeet, Whisper, and Apple Speech Analyser, and uses Apple Intelligence for simple reading and filler word removal. This local model allows apps to require ultra-fast latency of 80ms. This means that the text appears immediately after you speak.
audio pen
AudioPen started out as a web-based voice memo app, but has evolved over the years. Now with the Mac version, you can dictate text and rewrite it in any format and style you want, and switch between different styles at any time. In addition to real-time transcription, AudioPen lets you store audio notes across platforms, combine notes for summaries, upload audio files, and use AI to retranscribe existing notes. The app costs $33 for 3 months, $99 for 1 year, and $159 for 2 years.
If you purchase through links in our articles, we may receive a small commission. This does not affect our editorial independence.
