Developers
Dictate commit messages, code comments, docs and long AI prompts without leaving your editor — VS Code, Cursor, the terminal, anywhere you type.
AI voice-to-text · 100% on-device · Free forever
Think out loud. We'll type it.
Private, on-device dictation in Languages DijiFlow transcribes DijiFlow transcribes speech in 90+ languages, fully on-device. The 29 featured languages (marked ✓) also get advanced vocabulary tuning for the names and jargon of your field. Accuracy reflects typical results. Excellent accuracy Català Catalan中文 Chinese✓Čeština Czech✓Dansk Danish✓Nederlands Dutch✓English English✓Suomi Finnish✓Français French✓Galego GalicianDeutsch German✓Ελληνικά Greek✓Magyar Hungarian✓Bahasa Indonesia Indonesian✓Italiano Italian✓日本語 Japanese✓한국어 Korean✓Македонски MacedonianNorsk Norwegian✓Nynorsk Norwegian NynorskPolski Polish✓Português Portuguese✓Română Romanian✓Русский Russian✓Español Spanish✓Svenska Swedish✓Türkçe Turkish✓Українська Ukrainian✓ Good accuracy Afrikaans AfrikaansShqip Albanianالعربية Arabic✓Հայերեն ArmenianAzərbaycanca AzerbaijaniEuskara BasqueБеларуская Belarusianবাংলা BengaliBosanski BosnianБългарски Bulgarian粵語 CantoneseHrvatski CroatianEesti Estonianქართული Georgianעברית Hebrew✓हिन्दी Hindi✓Íslenska Icelandicಕನ್ನಡ KannadaҚазақ KazakhLatviešu LatvianLietuvių LithuanianBahasa Melayu Malay✓മലയാളം Malayalamमराठी Marathiفارسی PersianСрпски SerbianSlovenčina SlovakSlovenščina SlovenianTagalog Tagalog (Filipino)தமிழ் Tamilతెలుగు Teluguไทย Thai✓Tiếng Việt Vietnamese✓Cymraeg Welsh Usable accuracy አማርኛ Amharicঅসমীয়া AssameseБашҡортса BashkirBrezhoneg BretonFøroyskt Faroeseગુજરાતી GujaratiKreyòl Ayisyen Haitian CreoleʻŌlelo Hawaiʻi HawaiianBasa Jawa Javaneseខ្មែរ Khmerລາວ LaoLatina LatinLëtzebuergesch LuxembourgishMalagasy MalagasyMalti MalteseMāori MaoriМонгол Mongolianမြန်မာ Myanmarनेपाली NepaliOccitan Occitanਪੰਜਾਬੀ Punjabiसंस्कृतम् Sanskritසිංහල SinhalaBasa Sunda SundaneseKiswahili SwahiliТатарча Tatarاردو UrduOʻzbekcha Uzbekייִדיש Yiddish Experimental Hausa HausaLingála Lingalaپښتو PashtochiShona Shonaسنڌي SindhiSoomaali SomaliТоҷикӣ Tajikབོད་སྐད TibetanTürkmençe TurkmenYorùbá Yoruba ✓ Advanced vocabulary tuning (29 featured languages). Accuracy tiers are indicative, based on standard speech benchmarks; every language runs fully offline on all plans, including Free. . Speak in any app and your words appear instantly. No internet needed, and nothing leaves your machine. On Mac and Windows.
Free forever · No account · No internet needed
Model & performance
Built on Whisper, running fully on your device.
DijiFlow runs OpenAI's Whisper speech models entirely on your device — Apple's Neural Engine and GPU on Mac, plus AMD, Intel and NVIDIA GPUs on Windows. 90+ languages, fully offline. Nothing is ever uploaded.
Transcribes 90+ languages entirely on your device, with advanced vocabulary tuning for the 29 most-spoken. See Languages DijiFlow transcribes DijiFlow transcribes speech in 90+ languages, fully on-device. The 29 featured languages (marked ✓) also get advanced vocabulary tuning for the names and jargon of your field. Accuracy reflects typical results. Excellent accuracy Català Catalan中文 Chinese✓Čeština Czech✓Dansk Danish✓Nederlands Dutch✓English English✓Suomi Finnish✓Français French✓Galego GalicianDeutsch German✓Ελληνικά Greek✓Magyar Hungarian✓Bahasa Indonesia Indonesian✓Italiano Italian✓日本語 Japanese✓한국어 Korean✓Македонски MacedonianNorsk Norwegian✓Nynorsk Norwegian NynorskPolski Polish✓Português Portuguese✓Română Romanian✓Русский Russian✓Español Spanish✓Svenska Swedish✓Türkçe Turkish✓Українська Ukrainian✓ Good accuracy Afrikaans AfrikaansShqip Albanianالعربية Arabic✓Հայերեն ArmenianAzərbaycanca AzerbaijaniEuskara BasqueБеларуская Belarusianবাংলা BengaliBosanski BosnianБългарски Bulgarian粵語 CantoneseHrvatski CroatianEesti Estonianქართული Georgianעברית Hebrew✓हिन्दी Hindi✓Íslenska Icelandicಕನ್ನಡ KannadaҚазақ KazakhLatviešu LatvianLietuvių LithuanianBahasa Melayu Malay✓മലയാളം Malayalamमराठी Marathiفارسی PersianСрпски SerbianSlovenčina SlovakSlovenščina SlovenianTagalog Tagalog (Filipino)தமிழ் Tamilతెలుగు Teluguไทย Thai✓Tiếng Việt Vietnamese✓Cymraeg Welsh Usable accuracy አማርኛ Amharicঅসমীয়া AssameseБашҡортса BashkirBrezhoneg BretonFøroyskt Faroeseગુજરાતી GujaratiKreyòl Ayisyen Haitian CreoleʻŌlelo Hawaiʻi HawaiianBasa Jawa Javaneseខ្មែរ Khmerລາວ LaoLatina LatinLëtzebuergesch LuxembourgishMalagasy MalagasyMalti MalteseMāori MaoriМонгол Mongolianမြန်မာ Myanmarनेपाली NepaliOccitan Occitanਪੰਜਾਬੀ Punjabiसंस्कृतम् Sanskritසිංහල SinhalaBasa Sunda SundaneseKiswahili SwahiliТатарча Tatarاردو UrduOʻzbekcha Uzbekייִדיש Yiddish Experimental Hausa HausaLingála Lingalaپښتو PashtochiShona Shonaسنڌي SindhiSoomaali SomaliТоҷикӣ Tajikབོད་སྐད TibetanTürkmençe TurkmenYorùbá Yoruba ✓ Advanced vocabulary tuning (29 featured languages). Accuracy tiers are indicative, based on standard speech benchmarks; every language runs fully offline on all plans, including Free. and their accuracy tiers.
Works offline · no internet neededmacOS 14 (Sonoma)+ · Apple SiliconWindows · AMD · Intel · NVIDIA GPUs90+ languages, fully on-device
~98%accuracy on clear speech (largest model)
15×faster than real time, on-device
29languages, offline
No servers100% on your device
300 MB–6 GBspeech model — base to Large-v3 (downloaded once)
~12 MBapp size — speech models download on demand
Who it's for
However you work, talk it into text.
From code to meetings, DijiFlow turns speech into text on your own hardware. Fast, private, free to start.
Podcasters & creators
Transcribe episodes and interviews locally, with speaker labels and timestamps on Pro. No uploads and no per-minute cloud fees.
AI & LLM workflows
Speak your prompts instead of typing them. Long, accurate, punctuated text straight into ChatGPT, Claude and Cursor — nothing logged anywhere.
Meetings & research
Record and transcribe meetings, lectures and interviews privately. Speaker identification tracks who said what — all on your machine.
Writers & students
Draft articles, essays, notes and emails at the speed of speech in any app, with vocabulary packs for the names and jargon of your field.
Email & messaging
Reply by voice in Gmail, Outlook, WhatsApp, Telegram, Slack and Messenger. One hotkey dictates into whatever window has focus, so you never switch tools.
Teams & business
Roll out private dictation across your org with volume and company licences. No audio leaves your people's machines — built for regulated industries. Business licensing →
How it works
Three steps, zero friction.
Press a hotkey, speak, and your words land as text wherever your cursor is — fully on-device.
1
Press the hotkey
Press your hotkey from anywhere on your computer.
2
Speak naturally
Talk the way you think — in any app, in any of 90+ languages.
3
Your text appears
Pasted at your cursor instantly — nothing ever leaves the device.
Productivity
Talk is faster than typing.
Most people speak about 3.7× faster than they type. DijiFlow turns that into finished text, and none of it leaves your computer.
≈3.7×
faster than typing — ~150 wpm spoken vs ~40 wpm typed
~3 hrs
saved a week — at 2,000 words/day, speaking takes ~13 min vs ~50 min typed
~93%
less time on a 1-hour meeting transcript — ~4 min, not an hour
£0
to start — Free forever, no account, no card
Pricing
Start free. Go Pro when you're ready.
Free forever, no account. Upgrade to Pro for unlimited length, the largest models and speaker labels — one app, pick your term.
Free
£0
forever
No account, no card. Yours to keep.
1 licence · 1 device
One licence activates one device — grab a few: one for your Mac, one for your PC, one for home, one for work. Every extra device is 20% cheaper.
Need 6 or more? Talk to Enterprise →
Download for MacmacOS 14+ · Apple Silicon
Download for WindowsWindows 10 / 11
Includes a 30-day free trial of Pro — every feature unlocked, no credit card.
Volume licensing · central billing & one invoice · priority support · buy once, use forever
Hotkey slots1 slot3 slots
File length3 minUnlimited
File & video transcriptionNot includedTranslation missing: en.general.accessibility.included
Speaker labels & timestampsNot includedTranslation missing: en.general.accessibility.included
Vocabulary support · 29 languagesNot includedTranslation missing: en.general.accessibility.included
GPU / Neural Engine + largest modelsNot includedTranslation missing: en.general.accessibility.included
All 90+ languagesTranslation missing: en.general.accessibility.includedTranslation missing: en.general.accessibility.included
Private by design
Your words never leave your machine.
Every word is transcribed on your own device. Nothing is uploaded, nothing sits on a server, and you don't need an internet connection once you're set up.
- No internet needed. It works completely offline
- Your audio and transcripts stay on your machine
- Keep a local history on your computer, only if you want one
- No account, no telemetry, no cloud copy
What customers say
Trusted by people who talk for a living.
4.8
/ 5·Based on
232 reviews
DM
Verified
Use it all day on my Mac and miss it the moment I pick up my phone. An iPhone companion would make it perfect. Still excellent as it is.
Review for
DijiFlow Dictate — Pro
TN
Verified
I dictate a few paragraphs every evening. Private by design, so I'm honest in them. The habit stuck because it's so low friction.
Review for
DijiFlow Dictate — Pro
IG
Verified
Short dictations land before I've moved my eyes back to the screen. The responsiveness changes how willing I am to use it for tiny things.
Review for
DijiFlow Dictate — Pro
ST
Verified
Adding my own terms works really well and fixes the words other apps get wrong. I'd just like room for an even longer vocabulary list. Otherwise top notch.
Review for
DijiFlow Dictate — Pro
HC
Verified
Was paying way too much monthly for transcription. One lifetime payment here and I own it. No regrets at all.
Review for
DijiFlow Dictate — Pro
Questions
Frequently asked questions
Yes — the Free tier is free forever, with no account or card. Pro adds more slots, unlimited file/video, speaker labels and the largest models, with a 30-day free trial.
No. Transcription runs 100% on your machine. The internet is only used once, to download a speech model the first time.
DijiFlow runs on Mac and Windows (macOS 14+ on Apple Silicon, or Windows 10/11). One licence covers both.
Only to detect your global dictation hotkey. DijiFlow does not read what you type in other apps.
Talk instead of type
Free forever to start.
Download DijiFlow Dictate free for Mac or Windows, or try every Pro feature free for 30 days. Mac and Windows.
Free forever · No account · No internet needed