FlowVoice — part 4 (words to recognise)

What it is

A speech engine that hears an unfamiliar name writes the nearest ordinary word instead — "initial" for "Omniscio", "sequel" for "SQL". FlowVoice can send a list of expected words with every dictation on the cloud engine, so the engine spells them right at the source rather than the app patching the text afterwards. There are two lists: the words you keep yourself, and the words Omniscio learns from the corrections you make. Other engines ignore both. Part 1, flowvoice.md, covers the hotkeys, the speech engines and the settings card.

Where to find it

Settings → Voice Control, under the Dictation (FlowVoice) heading, in the Words to recognise card: your own list first, then the Learn from my corrections switch and the Learned from your corrections list. Right-clicking the mic button in a session's message box opens the same card over the session, and searching Settings for "learned words" finds it.

How it behaves

Your own list (custom words)

Under Settings → Voice → FlowVoice, Words to recognise is a list of the names, brands and jargon dictation keeps getting wrong. The list is sent with every dictation to the cloud speech engine (the company's speech router — Soniox, or its Meta Muse backup when Soniox refuses or fails before the first word) as words to expect, so the engine spells them right at the source instead of the app patching the text afterwards. A word added there is in force on the very next dictation; other engines ignore the list.

The list starts filled from your own past dictations on this computer: a one-time local pass reads the transcripts already saved for your dictations and proposes the names and jargon that recur in them. Nothing leaves the machine for it and no model is called. Everything proposed is yours to edit or remove, and the pass never runs again — a list you change stays exactly as you left it. Blank entries, duplicates that differ only in case, and words over 64 characters are dropped, and the list holds up to 200 words and 4,000 characters in total. If a list is ever too long or malformed the dictation still runs; only the words are dropped. The list is never written to a log.

Learned from your corrections

When you dictate into a session's message box in Omniscio, fix a name the engine got wrong (say "initial" or "omniscient" to "Omniscio") and send the message, straight away or queued, the name you typed is remembered. It goes on a separate Learned from your corrections list under Words to recognise, and from then on it is sent to the cloud engine as a word to expect, right after your own words. Learning only ever adds expected words: it never changes what a dictation types, never edits your own list, calls no AI model, and never reads another app.

• What it learns. Only a short replacement that looks like a name, brand or acronym: a word capitalised mid-sentence ("Omniscio"), one with a capital inside it ("GitHub"), a short acronym of up to five capitals and digits that replaced a different word ("sequel" to "SQL"), or a name carrying a digit that starts with a letter ("S3"). At most five words from one message.
• What it ignores. Rewording to ordinary words, a capital at the start of a sentence, an ordinary word written in capitals ("OK"), a word written in capitals for emphasis ("FAILED", "NEVER"), a dictated word you only shouted, numbers such as "2nd" or "5pm", a word you only added or deleted, and a message that does not contain most of the dictation. One limit remains: a short word in capitals typed over a different word ("big" to "HUGE") can still be learned — remove it and it stays gone.
• Where it looks. Only a dictation pasted into one of Omniscio's own windows, compared with the message you then send from a session's message box. A quick reply never teaches, and fixes made in another app, Team Chat or the search box are not seen.
• Removing a word. Each learned word has a remove button. A removed word is never learned again on its own — you can still add it to your own list.
• The switch. Learn from my corrections, on by default, stops all learning and forgets the dictations it was holding. The learned list stays visible and removable.
• Room. Your own words and the learned ones share the engine's 200-word, 4,000-character limit, your own words first. A word is learned only when there is room for it, and when your own list grows, the learned words that no longer fit leave the learned list (the newest first), so the list on screen is exactly what the engine receives. A learned word you add to your own list leaves the learned list too.
• Privacy and speed. At most your last five dictations are kept for the comparison, in memory only, and each is dropped fifteen minutes after it was pasted. No dictation, message or learned word is ever written to a log or telemetry — a learned word is counted, never named. The comparison runs only after your send has been answered and is strictly bounded, so it never slows or fails a send.

For agents

Both lists are part of the FlowVoice settings, read with GET /flowvoice/settings and changed with PATCH /flowvoice/settings (a partial update; an unknown key is a 400).

• customWords is the person's own list. A PATCH that carries it replaces the whole list, and also drops any learned word that no longer fits beside it.
• learnFromCorrections is the switch: readable and writable.
• learnedWords and forgottenWords (the lower-case words the person removed) are read-only: a PATCH that names either is refused with a 400, so a stale settings screen can never wipe a word learned while it was open.
• forgetLearnedWords: ["word", …] is the one way to remove learned words: it takes them off the learned list and remembers them as forgotten, so they are never learned again.
• Telemetry records a word_learned event per learned word under FlowVoice, with no word in it.

The rules for the person's own list live in the repository's .claude/memory/contracts/flowvoice-custom-words-contract.md, and those for learned words, each with the tests that hold it, in .claude/memory/contracts/flowvoice-learned-words-contract.md.

Related

The main FlowVoice page, FlowVoice, covers the hotkeys, the speech engines and what they cost, and FlowVoice — part 3 covers how a dictation is delivered and the history list. The in-app microphone — talking to a session rather than typing at the cursor — is on Voice and TTS.