What chat supports today
The chat composer is the box at the bottom of every conversation. It does three things:Type a message
Enter text and press Enter to send. Shift+Enter adds a newline. Messages can be up to a few thousand characters.
Pick a model
Choose which language model answers — from ModuleX-managed models to your own provider keys.
Send and stream
Send the message and watch the reply stream back live, including any tool steps the Assistant takes.
Speak your request with device dictation
To talk to ModuleX instead of typing, use your device’s built-in dictation to enter text into the composer, then send it like any typed message.1
Open the composer and start dictation
Open a chat and start your operating system’s dictation — for example the microphone
key on a phone keyboard, or your desktop’s voice typing.
2
Speak your request
Your device converts your speech to text directly in the composer, the same as if you
had typed it.
3
Send the message
Press Enter (or the Send button). The reply streams back the same way it does for any
text message.
Device dictation is your operating system’s feature. Your device converts speech to text
locally or through its own service, and ModuleX only receives the resulting text — so
accuracy, languages, and limits are entirely your device’s.
How chat answers your message
However your text gets into the composer — typed or dictated — a single chat can answer it in three ways. You do not pick a mode; the chat decides based on what you ask and what you have connected.Assistant chat
The default. An agentic chat that reasons, calls your connected tools step by step, and pauses for your approval when needed.
Run a workflow
Trigger a saved workflow from a message and watch the run unfold inside the thread.
Chat with knowledge
Ask a question and get an answer drawn from your connected knowledge bases, with the sources it used.
Who can use chat: the chat surface requires an owner or admin role in the
organization. See roles and permissions.
Where to go next
Chat overview
How chat works end to end — the three ways a conversation is answered, and how replies stream.
Choose a model
Pick which language model answers your chats, from managed models to your own keys.
Chat with your knowledge
Attach a knowledge base and get answers grounded in your own documents.
Meet the Assistant
The agentic chat behind the default experience — how it reasons, calls tools, and asks for approval.