1
Pick your hotkey
Setup takes a minute. Choose the key combination that suits you, and dictation is one keypress away in every application you use.
SayToTypeDictate anywhere. Record your calls. Transcribe any recording.
Three tools in one app: press a hotkey and speak to write in any application, record a call and get a transcript with the participants' names, or drop in a recording and get a full transcript with speakers, timestamps and subtitles.
Speak instead of type. Keep every call. Read what you already recorded.
Voice typing on all four platforms. Call recording and file transcription run on Windows and macOS.
Voice typing in any app
Press a hotkey and speak. The finished text lands where your cursor is — browsers, messengers, documents, code editors or the terminal.
2
Speak into the app you are already in
Advanced speech recognition turns your voice into accurate, editable text and inserts it straight into whatever you are working in. No copy-paste, no switching windows.
3
Set the language, the translation and the tone
A mode fixes the input language, the output language and a prompt that shapes the result — meeting notes, a formal email, or a reply translated as you speak it.
Record your calls and meetings
Zoom, Teams, Google Meet — and FaceTime on a Mac. No bot joins the call, and the transcript says who said what.
Call recording runs in the desktop app for Windows and macOS.
No bot joins your call
Press Record and the call is recorded on your computer — your own words from your microphone, everyone else's from the call itself. Nothing is recorded until you press Record, and the offer itself is one checkbox away in the tray menu.
Who said what, in their own names
The names are not invented: the app reads the call's participant list while it records, so the transcript says who said what instead of Speaker 1 and Speaker 2. A line it cannot place is left without a name rather than given the wrong one, and any name can be corrected by hand.
Hands-free from start to finish
While the recording runs, a small bar shows the time: pause it, put it out of sight, or throw the recording away. When the call ends, the recording stops by itself and the transcription starts without you. Recorded calls live in a window of their own: play a call back with the transcript, search by participant or by any word in it, edit, translate and export it as text — just like a transcribed file.
Turn recordings into text
Meetings, interviews, lectures, videos — audio and video files alike: MP3, WAV, M4A, AAC, FLAC, OGG, OPUS, MP4, MOV, WEBM and more.
File transcription runs in the desktop app for Windows and macOS.
Drop in a file, get a transcript
Long recordings are split at natural pauses and transcribed part by part, with progress you can watch and cancel at any point. Search across every transcript you have made, or inside a single one. More on transcribing video and audio files
Speakers told apart automatically
Speakers are told apart and labelled, so an interview or a meeting reads as a conversation instead of a wall of text. Rename a speaker everywhere, or hand a single line to a different one.
TXT, SRT and VTT out of the box
Copy the result, or export it as plain text, SRT or VTT subtitles — with or without speaker names and timestamps, for calls and files alike. Play the recording back with the spoken line highlighted and correct any line by hand. More on making SRT and VTT subtitles
Subtitles in a second language
A finished transcript — of a call or a file — can be translated into another language on a tab beside the original. Timestamps and speaker names carry over, so subtitling a video in a second language takes a couple of clicks.
Key Features
Everything you need to speak instead of type, to keep every call, and to read what you have already recorded
Fast Transcription
Voice to text in seconds — fast speech recognition with low latency.
47 Languages
Speech recognition in 47 languages, with automatic language detection.
Works in Any App
Voice input for browsers, messengers, documents, code editors and the terminal.
Automatic Pasting
Speak to type directly into any text field — the text appears where your cursor is.
Call Recording
Record calls in Zoom, Teams and Google Meet with no bot in the call — the transcript is ready after the call.
Participant Names
Names in a call transcript are read from the call itself — not Speaker 1 and Speaker 2.
Calls Library
A window of recorded calls: search by participant or word, edit, translate and export.
Audio and Video Files
Transcribe MP3, WAV, M4A, AAC, FLAC, OGG, OPUS, MP4, MOV, WEBM and more.
Speaker Labels
Speakers are told apart and labelled, so a meeting reads as a conversation.
Playback and Editing
Play a recording back with the spoken line highlighted, and correct any line by hand.
Subtitle Export
Export transcripts as text or SRT/VTT subtitles, with speaker names and timestamps.
Transcript Translation
Translate a finished transcript — timestamps and speakers carry over to the subtitles.
Search
Search across every transcript you have made, or inside a single one.
Custom Hotkeys and Modes
Start dictation with one keypress, and create modes that fix the language, translate your speech or shape the result with a prompt.
Use Your Own API
Connect OpenAI, Mistral AI, Deepgram or any OpenAI-compatible provider.
Inside the App
Your recognition, your rules
Choose who does the recognition
Use SayToType Cloud, or connect OpenAI, Mistral AI, Deepgram or any OpenAI-compatible provider. A file or a call transcribed through your own key spends no minutes from your plan.
Settings that stay out of the way
The app lives in the system tray: pick your microphone, decide what happens while you record, and it stays invisible until you press the hotkey.
Who it's for
Everyone who talks faster than they type, everyone whose day is made of calls — and everyone sitting on recordings nobody has time to listen to
Anyone working with AI
Prompts, instructions and follow-up questions are long, and far faster spoken than typed — a paragraph of context costs you a sentence of breath.
Anyone who lives in messengers
Slack, Teams, Google Chat, Discord: reply at the speed you would say it, without taking your hands off what you were doing.
Anyone whose day is made of calls
Stand-ups, candidate interviews, customer calls: instead of taking notes while somebody else is talking, press Record and get a transcript afterwards that says who said what and can be searched.
Journalists and researchers
Hours of interviews become searchable text with speakers told apart, so a quote is a search away instead of a re-listen.
Students and professionals
Lectures and meeting calls turn into notes you can read, search and quote the same day they happened.
Podcasters and video makers
Subtitles in SRT or VTT, with timestamps that survive translation — captioning an episode in a second language is a couple of clicks.
Developers
Speak your code comments, commit messages and pull request reviews without leaving the editor or the terminal.
Frequently asked questions
What people ask before they download
Which audio and video formats can SayToType transcribe?
MP3, WAV, M4A, AAC, FLAC, OGG, OPUS, MP4, MOV, WEBM and more. Audio and video both work, and long recordings are split at natural pauses and transcribed part by part.
How many languages does the speech recognition support?
47. You can fix the language for a mode or let the app detect it, and a mode can also translate your speech into another language as you dictate.
Does voice typing work in any application?
Yes. Press the hotkey, speak, and the finished text is inserted where your cursor is — browsers, messengers, documents, code editors or the terminal. No copy-paste, no switching windows.
Does it tell speakers apart?
Yes. In a file transcription speakers are told apart and labelled, so an interview or a meeting reads as a conversation. In a recorded call the lines carry the participants' real names, read from the call itself. You can rename a speaker everywhere, or hand a single line to a different one.
Can it record my Zoom, Teams or Google Meet calls?
Yes. When a call starts in Zoom, Teams or Google Meet — or FaceTime on a Mac — SayToType offers to record it. No bot joins the call: the recording is made on your computer, stops by itself when the call ends, and comes back as a transcript with the participants' names.
Does SayToType tell the other participants that the call is being recorded?
No. Nothing is announced in the call and no bot appears in it. Telling everyone on the call that it is being recorded, and getting their consent where the law requires it, is your responsibility — the panel reminds you of this before you press Record.
Read the Terms of ServiceCan I get subtitles for a video?
Yes. Any transcript exports as SRT or VTT subtitles, with or without speaker names and timestamps. Translate the transcript first and the timestamps carry over, so a second-language subtitle track is a couple of clicks.
How subtitle export worksCan I use my own OpenAI or Deepgram API key?
Yes. Alongside SayToType Cloud you can connect OpenAI, Mistral AI, Deepgram or any OpenAI-compatible provider, and a file transcribed through your own key spends no minutes from your plan.
Which platforms does SayToType run on?
Voice typing, call recording and file transcription all run in the desktop app for Windows and macOS. Dictation is also available on iOS and Android, in beta.
Is there a free plan?
Yes. Every account gets a monthly allowance of cloud transcription at no cost, and dictation, recorded calls and file transcription draw on the same balance — a one-hour call costs an hour of it. Paid plans add more minutes, and your own API key costs no minutes at all.
See plans and pricesReady to stop typing?
Voice typing in every app you use, a transcript with names for every call, and text for everything you have already recorded
3-4x
Faster than typing
47
Languages supported
<2 sec
Processing time
Interface available in 15 languages:
Bulgarian · Czech · Dutch · English · French · German · Italian · Polish · Portuguese · Romanian · Russian · Slovak · Spanish · Swedish · Ukrainian