Speech recognition

Installed separately, as part of the Speech Recognition bundle: this module does not come with the app installer. Open Module Catalog → Add-ons and press Install on the Speech Recognition card, and the bundle installs all of its modules at once.

What this page is

Voice control for your stream: you say what you want out loud, and the smart AI assistant does it. Starting predictions by voice, running a poll, switching an OBS scene, changing the title and category, cutting a clip, writing a line in chat, flipping a smart plug — all of it without letting go of the mouse mid-game.

Two screens set it up, and they answer different questions:

• Voice → Speech recognition — how the app hears you: microphone, language, when to listen, what you call the bot.
• Chat Bot → Voice control — what the bot is allowed to do once it heard you.

Recognition runs on your own machine, so the sound never leaves the computer. Only the request itself goes to the AI, and only after the app decides you were talking to the bot — and that request is the part you pay for.

How to set it up

1. Pick a recognition model

Voice → Speech recognition, the Recognition model block. Pick one and press Download — it is a one-off download, after which recognition works offline. The row for each model says how much memory it takes and how fast it runs on your graphics card and on your processor: pick the one whose numbers you can live with, not the biggest.

Until a model is downloaded nothing is heard, and the tile says Recognition is not ready — not silence, a missing model.

2. Microphone and language

The Microphone and language block. Find microphones shows their real names; without it the system default is used.

Set Language you speak. Leaving it on Detect automatically makes every phrase go through a second pass, so recognition is about twice as slow.

3. Choose when to listen

The When to listen block, and this is the choice that matters most.

• Hold a key — the microphone opens while the key is held and closes when you let go. Assign the key with Assign; it is not taken away from other programs, so it keeps working inside the game. Everything you say while holding goes to the bot, and no name is needed: the key itself says you are talking to it.
• Always — the microphone stays open for the whole stream. Now the app has to tell your own speech apart from a request, and that is what the bot's name is for.

4. Name the bot, if the microphone stays open

The How you call the bot block. Say the name and the rest of the sentence goes to the bot: "Nova, start a poll".

Leave the name empty and every phrase you say goes to the bot — and every one of them costs credits. The screen says so in red while the microphone is open and the name is missing. With Hold a key an empty name is fine: the key is the trigger.

5. Word that stops the voice over

Say it while the bot is talking and it goes quiet at once. The name is not needed here — by the time you have said it, the bot has finished. Only the word on its own counts: "stop, and change the title" is a request, not the stop word.

Leave the field empty and the word for the language you speak is used: stop, стоп, alto, pare, stopp.

The word stops everything the app is reading, not only the bot. It does what Stop on the Voice over: Queue tile does: the line being spoken is cut off and the whole queue is thrown away, donations and subscriptions that were waiting their turn included. They are not read later. If you only want to cut the current line, press Skip on that tile instead.

6. Allow the actions you want

Chat Bot → Voice control. Every action is a card with its price in credits and a switch. Anything that cannot be undone starts switched off.

There is no list of phrases you have to learn. The most common commands are recognised on your own computer without the AI: saving a clip, switching to a scene or turning a smart plug on or off by its name, ending a poll, locking a prediction and cancelling one. They run at once and cost nothing. Everything else goes to the AI, which works out what you meant, so "cut a clip" and "save this moment" reach the same action as "clip that". The names it can use — OBS scenes, control panel buttons, smart plugs, prediction outcomes — come from what is actually connected, so it cannot invent a scene you do not have.

What it can do

Twelve, and that is the whole list. Clips, the title, polls and predictions go through Twitch; on YouTube and Kick the assistant writes in chat, switches scenes and presses panel buttons. One phrase is one action: "lock the betting and switch the scene" does only the first of the two.

Anything that is not an action is an ordinary answer: ask what the weather is, how long the stream has been going, what you played last week, what your chat commands are, what you asked a minute ago.

Only your voice can ask for an action

The Who may ask block on Chat Bot → Voice control says it in two lines: Your voice gets the actions, Chat, anyone in it gets conversation only. A viewer or a moderator who writes "start a prediction" or "clip that" to the bot in chat gets an answer in words and nothing happens, however the message is worded. The same goes for your own account in chat: in chat the bot is not given the actions at all, and the only way to ask for one is your microphone.

Ask before anything that cannot be undone

Switched on by default. The bot names the outcome — "Resolving the prediction: 'We win'" — and waits for a "yes". It names the outcome and not the action on purpose: what you are confirming is the thing you cannot take back.

Switch it off and the bot just does it. Quicker, and there is no taking it back.

Where you see what happened

The Stream: Voice tile on the control panel keeps the feed: your phrases and the bot's answers, in order. The colour of the stripe on the left says how it ended — blue for an answer, green for something done, amber for a question back, red for a refusal with the reason next to it.

By default the bot says the short version out loud — "Poll started" — and the details go to that feed. If you have no second screen to read them on, switch on Read the whole result out loud on the Voice control screen.

Five buttons in the tile's header:

• microphone — switches between hold a key and always, the same setting as on the recognition screen;
• speaker — read answers out loud or leave them as text in the feed. It is the same switch as Read answers out loud on the Voice control screen;
• Copy the feed — puts the whole feed on the clipboard, each line with its time and who said it;
• Clear the feed — empties the feed on the tile. Nothing else changes: actions already done stay done;
• power — the outermost one: the bot goes quiet, recognition stops and the model leaves memory. Scenarios triggered by donations and channel points are not affected — they never needed the microphone. Only scenarios triggered by a spoken phrase stop.

While you are live, the header also shows a counter such as 12 💎 this stream: the credits the voice assistant has spent since this stream started. Chat answers are not in it. The counter starts from zero with the next stream and is hidden while you are offline.

What it costs

Voice control is a paid feature. The half that listens runs on your own machine and adds nothing to the bill; the half that understands you and acts is the AI, and that is the half you pay for.

• Common commands cost nothing. Saving a clip, switching a scene or a smart plug by name, ending a poll, locking a prediction and cancelling one are recognised on your computer and run without the AI, even with no account and a zero balance.
• Everything else is two requests to the AI, not one: a cheap parsing step that repairs what was heard and decides whether the internet is needed, and the answer itself. The price on each action's card is what it costs when the AI carries it out.
• Recognition itself is not charged. It runs on your machine, so an open microphone costs nothing until you actually address the bot.
• A web search is ten credits. It only happens when the question needs facts from the internet, and only if Allow web searches is on.

When it does not work

Nothing is heard at all. Check the model is downloaded, then use Check the microphone — say a phrase within four seconds and the app shows what it heard. If it shows nothing, raise Input gain or lower the Speech threshold. If the status card or the Stream: Voice tile says No microphone found, the app sees no microphone at all: plug one in. With Hold a key, press the key again; with Always, listening comes back by itself. Check the microphone gives the same answer at once, and raising the gain will not help here.

The bot answers every phrase. The microphone is on Always and the name is empty. Give it a name, or switch to Hold a key.

The bot hears you but does nothing. The action is switched off on the Voice control screen, or the platform it needs is not connected — the card says which one.

It says "I did not catch which scene you meant". The name it heard does not match anything connected. Scene names come from OBS, button names from the control panel; say the name as it is written there.

It answers about the wrong thing, though it heard you right. Before answering, the app repairs misheard words against the names it knows — scenes, devices, buttons — and a rare word of your own can be swapped for one of them. Add that word on Voice → Speech recognition, on the Names it should get right tab: the repair step reads that list too, and a word from it is never replaced.

The microphone list says "Previously chosen microphone (not found)". The saved microphone does not match any device the system lists right now. When the microphone opens, the app first looks for the same device by its name, and if it is there, keeps using it and remembers it again. If it is really gone, recognition switches to the system default, and both the status card on this page and the Stream: Voice tile say The chosen microphone was not found; the card also names the microphone used instead. Plug yours back in: with Always the app switches back by itself, with Hold a key on the next press. To use another one, press Find microphones, pick it and save. If there is no microphone at all, recognition has nothing to listen to, and both say No microphone found.

It says "Recognition did not start". The engine could not load, and the microphone has nothing to do with it — the line underneath says what the system reported. Update the app first: builds before 0.14.2 shipped without one of the Windows runtime libraries, and on a clean Windows recognition could not start at all. If the message stays after the update, send the logs to support together with that line.