Speak anywhere you can type.
Free. Offline. Private.
EchoQuill is free, open-source voice dictation for Windows. Your words appear live as you talk — powered by local Whisper AI. No subscription, no account, and your voice never leaves your PC.
⬇ Download Free for Windows See Pro — $5/moEverything the paid apps do — free
Built as an open-source alternative to Wispr Flow and Dragon, with the features they charge for.
Live dictation, any app
One hotkey. Words appear as you speak, then land wherever your cursor is — email, Word, browser, chat.
100% offline & private
Local Whisper AI runs on your PC. No cloud, no account, no audio ever uploaded. Ever.
Voice commands
"Computer, open Chrome." "Volume up." "Select all." Control your PC hands-free with a safe, fixed command list.
Rewrite by voice
Highlight any text, speak an instruction — "make this more professional" — and it's rewritten in place.
Video → text, in bulk
Paste one link — or a whole list. YouTube, Shorts, TikTok, 1,800 sites, or your own files. Auto-saved, titled, and searchable with timestamps: "4 matches — at 02:14, 05:37."
Clips you control
Click a clip to paste it right where your cursor is, or drag it anywhere. Search, multi-select, delete — and edit any past transcription and save it. No other app does this.
Custom dictionary
Names, jargon, brands — always right. It even learns from your repeated corrections automatically.
AI is optional (and rarely needed)
The built-in transcription is excellent on its own — most people never turn AI on. If you want it, plug in Claude, OpenAI, Groq, Ollama, DeepSeek, Qwen or GLM to auto-format emails and notes. Off by default.
Light, dark or system
A theme that matches your taste — or follows Windows automatically.
Optional audio history
Keep private local recordings of your dictations with a size budget and one-click ZIP export. Off by default.
Stats & self-update
Words per day and time saved vs typing — stored only on your PC. The app updates itself with one click.
99 languages
Powered by Whisper — from instant "tiny" to maximum-accuracy models covering 99 languages.
Get updates & the Pro launch discount
One or two emails a month. New features, new versions, and first dibs on Pro pricing.
How it stacks up
Everything below is in the free version.
| EchoQuill | Wispr Flow | Dragon | |
|---|---|---|---|
| Price | Free forever | $12+/mo | $200–700 |
| Works offline | Yes | No | Partly |
| Voice leaves your PC | Never | Yes | Configurable |
| Open source | Yes (MIT) | No | No |
| Voice-control your PC | Yes | No | Yes |
| Rewrite selected text by voice | Yes | Yes | Limited |
| Video / YouTube transcription | Yes | No | No |
| Batch-transcribe a list of URLs | Yes | No | No |
| Timestamped transcript search | Yes | No | No |
| Clipboard manager, drag & drop | Yes | No | No |
| Click a clip to paste at your cursor | Yes | No | No |
| Edit & manage transcription history | Yes | No | No |
| Per-app tone (Slack casual, Outlook formal) | Yes | Yes | No |
| Optional bring-your-own AI (not required) | Yes | No | No |
| Light / dark / system theme | Yes | Yes | Yes |
| Optional local audio history | Yes | No | Partly |
| One-click self-update | Yes | Yes | Yes |
Simple pricing
Dictation is free forever. Pro removes the limits for power users.
Free
- Unlimited dictation, everywhere
- Voice commands & rewrite-by-voice
- 5 video transcriptions
- Last 10 clips in the tray
- Open source (MIT)
Pro
- Everything in Free, plus…
- Unlimited video transcriptions
- Drag-and-drop file upload → auto-transcribe
- Ask AI about any video (timestamped answers)
- Unlimited clip library, 50 at a time
- Favorites tab — pin your best clips
- Priority support
- Keeps the free version alive ♥
Questions
Do I need to set up AI or an API key?
No. EchoQuill's built-in local transcription (OpenAI Whisper) is excellent on its own — most people never enable AI at all. The optional AI layer only adds smart formatting (turning a spoken email into a laid-out email, or notes into bullets). It's off by default, and plain dictation is often the cleaner result.
Is it really free? What's the catch?
Really free, and open source under MIT — you can read every line of code on GitHub. Pro exists for power users who want unlimited video transcription and a bigger clip library; that's the whole business model. No ads, no data selling.
Does my voice go to the cloud?
No. Speech recognition runs entirely on your PC with OpenAI's open-source Whisper model. The only network use is the one-time model download — unless you deliberately enable a cloud AI provider with your own key.
What do I need to run it?
Windows 10 or 11 and a microphone. Download, run, grant mic access, press Ctrl+Alt+Space, and talk. An NVIDIA GPU makes it faster but isn't required.
Windows says "unrecognized app" when I install — why?
New open-source apps aren't code-signed (certificates cost hundreds per year). Click "More info → Run anyway." The code is public on GitHub for anyone to inspect — that's better transparency than a signature.
How accurate is it?
Whisper is the same family of models behind most modern transcription services. Pick your speed/accuracy tradeoff in Settings — from instant "tiny" to 99-language "maximum accuracy" for videos.