SpeakoFlow

Free, open-source offline voice dictation and AI assistant

121 followers

Free, open-source offline voice dictation and AI assistant

121 followers

Visit website

AI Dictation Apps

•

Realtime Voice AI

SpeakoFlow puts your voice over your whole desktop. Speak, and your words land in any app — email, editor, chat, terminal. Say "Hey Flow" and it writes the whole reply from what's on your screen. Ask the assistant about what you're looking at and hear the answer back. It also cleans up your dictation, translates as you speak, and learns how you work. Everything can run on your machine — speech-to-text always does. Free, open source, MIT. Windows, macOS, Linux.

This is the 2nd launch from SpeakoFlow. View more

SpeakoFlow Mini

Launching today

Tiny local model that fixes dictation without rewriting it

Dictation cleanup has two halves. Fix what the speaker actually got wrong, and leave everything else exactly as dictated. General models fail the second half: hand them a sentence that is already correct and they improve it. A comma becomes a full stop, a paragraph becomes bullets. SpeakoFlow Mini is 0.8B, Apache-2.0, 833 MB, and runs offline on a desktop CPU. Already-correct text comes back untouched 92.6% of the time. No API, no reasoning tokens, no rewriting.

Free

Launch tags:Open Source•Artificial Intelligence

Launch Team / Built With

Viktor.comAn AI coworker that actually does the work

Promoted

SpeakoFlow

Maker

📌

Hi everyone! 👋 I make SpeakoFlow, a free offline voice assistant. This is the small model that cleans up what you dictate, and I trained it because nothing else would leave my text alone. Speech recognition is good now. Punctuation, capitals, fillers and numbers are already handled. So the only job left is fixing what you actually got wrong. Say "let's ship it Thursday, no, Friday" and you want "let's ship it Friday". Say something that was already fine and you want it back untouched, character for character. That second half is where everything I tried fell over. A capable model handed correct text will improve it. A comma becomes a full stop, a paragraph becomes bullets, a word becomes a smoother synonym. Each edit looks reasonable on its own and each one is wrong, because I said the other thing and now I am undoing it by hand. I did get it working with a large hosted model behind an API. That meant a network round trip and a bill every time someone dictated a sentence, for a feature that runs while you wait for text to appear. So I trained a 0.8B to do the narrow version of the job instead. It is 833 MB, Apache-2.0, and runs on an ordinary CPU with no internet. Already-correct text comes back untouched 92.6% of the time. Being straight about the limits: on the strange cases real dictation throws up, a big hosted model still reads the situation better than this one does. What this does is get close on the cases that keep happening, at a size you can ship inside an app. Full results, limitations and a one-line Ollama command are on the model page. If you dictate something and it changes a line you wanted kept, or misses one you wanted fixed, send me the text. That is the feedback I want most.

Report

8h ago

Previous SpeakoFlow Launches

SpeakoFlowFree, open-source voice dictation and AI assistant, offline

Launched on August 4th, 2026