Free · MIT · Windows 10/11

Dictation on your hardware, not their servers.

Hold a hotkey, talk, release. Whisper transcribes on your own CPU or GPU, a local model polishes the text, and it lands at your cursor about a second later. No subscription, no account, no telemetry.

Download for Windows View source MIT licensed · 1577 tests
any app, wherever your cursor is
idle · 100% local

The privacy ledger

Network calls per dictation:

0

by default. architectural, not measured.

The dashboard keeps a local audit of everything that touches the network. Out of the box that list is empty: audio, transcripts, embeddings, and everything Echo Flow learns about you live in a SQLite file on your disk. The only cloud paths are opt-in, need your own API key, and are off until you flip them.

your audiothis machine
transcripts + historythis machine · data/history.db
everything it learns about youthis machine
cloud cleanupopt-in only · your key · off by default

How it works

Three moves. One second.

01

Hold Ctrl+Shift

A global push-to-talk hotkey that works in any focused window: email, Slack, your editor, a form.

02

Talk

Whisper runs locally, sized to your hardware (tiny through large-v3-turbo). CPU works; an NVIDIA GPU gets used automatically.

03

Release

A small local model strips the "um"s, fixes punctuation and casing, and pastes polished text at your cursor.

your machine · no network
mic-> Whisper-> local LLM cleanup-> your cursor-> history.db

no Ollama installed? you still get raw Whisper text. offline either way.

The part the others can't copy

It learns you. Locally. Forever.

Cloud dictation learns everyone a little. Echo Flow learns one person deeply, because all of your corrections stay on your disk where it can keep using them.

Fix it once, it sticks

Corrections you make feed a local pattern miner. Casing sticks after a single edit, recurring mishearings get learned (with a phonetic gate so paraphrases don't), and given enough history it can clean up with no LLM in the loop at all.

tiktok TikTok learned from 1 edit
note to vec node2vec phrase mishearing, learned

Calibrate to your voice

Read eight known sentences aloud and Echo Flow compares what Whisper heard against ground truth, pinning the words it fumbled straight into your dictionary. Accent adaptation at the text layer, no model fine-tuning.

heard "cooper netties" -> Kubernetes pinned

Humanize anything

Paste AI-written text, get plain prose back: dead openers cut, hedging stripped, long dashes gone. Sentences carrying numbers, citations, or quotes are never sent to the model, so your facts survive byte-for-byte.

It is important to note that results delve into significant improvements.
Accuracy went from 0.81 to 0.88. 🔒 figures kept exact

Voice actions, allowlist-only

"computer, open spotify" launches apps from a list you configured. URLs are restricted to http, https, and mailto. Nothing in the action layer deletes, sends, or pays, no matter what proposed the action.

$ "open downloads folder" -> allowed · on your list
$ "run this script" -> no such path exists

Compared

Echo Flow vs. the subscription apps

Echo FlowTypical cloud dictation app
Pricefree · MIT$10 to $30 / month
Your audiostays on deviceuploaded every time
Works offlineyesno
Account requirednonesign-up
Learns your correctionslocally, foreverlimited, cloud-side
AuditableMIT source + privacy ledgera policy page

Install

Two ways in.

Installer

Download the setup exe, run it, and hold Ctrl+Shift when the green mic appears in your tray. First launch fetches the Whisper model once; after that it works fully offline. SHA256 files sit next to every download.

Get the installer

From source

What CI tests, and the way to go if you want to hack on it. Python 3.11+.

git clone https://github.com/JOhnsonKC201/Echo_FLOW.git cd Echo_FLOW scripts\setup.bat run.bat

Recommended: Ollama + ollama pull qwen2.5:3b-instruct-q4_K_M for local cleanup.

Questions people actually ask

FAQ

Is my audio really never uploaded?

Audio is never uploaded, full stop: it stays in memory for the length of the utterance and is dropped. Your text can reach a cloud API only through paths you switch on yourself, each needing your own API key: Prompt-Engineering mode, the teacher loop, cleanup.allow_cloud_cleanup, the verify-escalation pass, and the humanizer's cloud option. Watch the third one in particular, because unlike a deliberate keystroke it applies to every dictation. The code is MIT, and the dashboard's privacy page shows which of these are live right now so you can verify instead of trusting.

Do I need a GPU?

No. Whisper model size is picked automatically for your hardware and runs fine on CPU. If an NVIDIA GPU is present it gets used, which mostly buys you headroom for the larger, more accurate models.

What does it cost?

Nothing. It is MIT-licensed and fully local. If you deliberately opt in to a cloud model with your own key, you pay that provider; otherwise there is nothing to pay anyone.

How is this different from Windows built-in Win+H?

Win+H is fine for short bursts. It does not clean up filler, learn your jargon and casing, adapt style per app, or give you push-to-talk that pastes anywhere. Echo Flow does all of that, on your hardware, with an audit trail.

Languages other than English?

Sixteen languages plus auto-detect. English currently gets the most of the learning machinery; the rest transcribe and clean up fine.