AI calling apps have come a long way in a short time. For years it was slow and wrong – unless you spoke in a certain way and pronounced clearly.
Advances in large-scale linguistic models (LLMs) and speech-to-text models have changed that, producing systems that can interpret speech more accurately while retaining enough context to format text correctly. Developers have also built in features to automatically remove filler words, correct typos, and manage punctuation — outputting text that requires very little editing.
Since there are tons of such apps on the market now, we’ve compiled our picks for the best and most useful calling apps available right now.
Wispr Flow
Wispr Flow is a well-powered AI summoning app that lets you add custom names and summoning commands. It has native apps for macOS, Windows, and iOS; Android version works.
The app lets you customize how it writes your text by choosing from “formal,” “regular,” and “more casual” styles for different types of writing, such as personal messages, work, and email. And if you use it with vibe-coding tools like Cursor, you can turn on the feature to automatically identify variables or tag files in the dialog.
The app lets you write up to 2,000 words per week for free on desktop, and 1,000 words per month on iOS. Paid subscription plans offer unlimited writing and start at $15 per month.
Willow
Willow advertises itself as a great time saver for those who don’t like to type. Along with common features such as automatic editing and formatting, the application uses large language models to generate a full passage of text from just a few spoken words.
Willow also takes a more privacy-oriented approach by storing all documents locally on your device and allowing you to completely opt out of model training. It also allows you to add custom words to help adapt to the words of your industry, or locale.
Willow allows you to dictate 2,000 words a month from your desktop app for free. Individual subscription plans start at $15 per month, unlock unlimited calling and make the app remember your writing style.
The Monologue
If privacy is important to you, Monologue lets you download its AI model directly to your device for recording, keeping your data completely off the cloud. In addition, the app allows you to customize its tone according to the app you are using.
Monologue lets you type 1,000 words a month for free; subscription costs $10 per month or $100 per year. The company is also sending its most active users a virtual shortcut device called Monokey to use with the app.
Speak up
Superwhisper is primarily a dictation app, but it can also transcribe from audio or video files. The app allows you to select and download AI models, including several of them at different speeds and levels of accuracy, as well as Nvidia’s Parakeet models for speech recognition.
The app also lets you write custom commands to direct the output, and you can view both processed and unprocessed transcripts directly from your system keyboard.
The basic voice-to-text feature is free to use, and you get 15 minutes to test Pro features like translation and transcription. The paid tier allows you to use your AI API keys and connect to cloud and local models without any usage caps.
A monthly plan costs $8.49 per month, an annual plan costs $84.99 per month, or you can pay $249.99 for a lifetime subscription.
VoiceTypr
The VoiceTypr app takes an offline-first, no-subscription approach, allowing you to use local models for transcription. It also has a GitHub repository for those who want to host and use the open source version themselves. VoiceTypr supports more than 99 languages and works on both Mac and Windows.
The app is available to try for three days for free, and after that, it will allow you to purchase a lifetime license. The app costs $35 for one device, $56 for two, 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 the category in terms of latency (the delay between when you speak and when the text appears on the screen).
Besides managing grammar and punctuation, Aqua also lets you auto-complete text by saying phrases – you can say “my address” and Aqua writes it, for example.
The app also offers its own speech-to-text API, allowing other apps to connect to Aqua’s transcription engine.
The free tier gets you 1,000 words per month. Paid plans start at $8 per month with an annual fee and unlock unlimited words and 800 custom dictionary values.
It is useful
Handy is an open source, free transcription tool that runs on Mac, Windows, and Linux. The app is pretty basic and doesn’t offer much customization, but if you want to start using your voice more and don’t want to pay, it’s a good option.
The app has a basic settings menu that lets you toggle push-to-talk and change the hotkey to enable transcription.
It has no type
Typeless stands out for its high free word count. The company says it does not store the data or use it to train AI models. Typeless also offers to rewrite sentences you may have dreamed up.
The app allows you to dictate up to 4,000 words per week (about 16,000 words per month) in its free section. You can pay $12 per month (billed annually) to unlock unlimited names and get access to new features. Typeless is available for Windows and macOS only.
VoiceInk
VoiceInk is an open source private calling app for Mac. The app supports global shortcuts for recording start/stop, and push-to-talk mode. It reads the context on the screen and adjusts the output accordingly.
The app can automatically detect specific apps and URLs and apply custom formatting or rules to each item. It also has an assistant mode that can answer your questions. The app costs $25 for lifetime access for one device, $39 for two devices, and $49 for three devices.
Dictato
Dictato is a Mac dictionary app priced at €9.99 — about $12 — that gives you lifetime access and two years of feature updates. The app works with offline models like Parakeet, Whisper, and Apple Speech Analyzer, and uses Apple Intelligence for light reading and removing filler words. Because of these local models, the application wants a very fast delay of 80ms, which means that the text appears almost immediately after speaking.
AudioPen
AudioPen started out as a web-based voice note app, but has evolved over the years. Its Mac version now allows you to cut text and rewrite it in your preferred format and style, switching between different styles at any time. In addition to live transcription, AudioPen allows you to save audio notes across platforms, combine notes for summaries, upload audio files, and rewrite existing notes using AI. The app costs $33 for three months, $99 for a year, and $159 for two years.
If you shop through links in our articles, we may earn a small commission. This does not affect our editorial independence.
