> For the complete documentation index, see [llms.txt](https://docs.ebrain.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ebrain.ai/chatting-with-tim/files-and-voice.md).
# Files, uploads, and voice
You don't have to paste everything into the chat box. You can attach files for Tim to read, or speak your message out loud and let him transcribe it. This page covers both.
## Attaching and uploading files
There are three ways to add a file to a message:
* Click the paperclip button (**Add file**) and pick a file.
* Drag a file onto the chat. A **Drop to upload** overlay appears while you drag.
* Paste an image straight from your clipboard.
### What you can attach
| Type | Examples |
| ------------- | --------------------------------------- |
| Images | screenshots, photos |
| Documents | PDF |
| Office files | Word (.doc, .docx), Excel (.xls, .xlsx) |
| Data and text | CSV, plain text (.txt) |
{% hint style="info" %}
You can attach up to **10 files per message**, and each file can be up to **10 MB**. If a file is too large or isn't a supported type, you'll see an inline error and it won't be added.
{% endhint %}
A small badge shows how many files are attached, and every file preview has a remove (✕) button so you can take one off before sending.
### What Tim does with your files
* **Images** are sent to Tim so he can actually see them and reason over what's in the picture.
* **Documents** are uploaded and indexed, so Tim can search and read their contents to answer your questions.
While your files are being prepared, you'll see status text rotate through messages like "Reading file...", "Analyzing document...", "Extracting text...", and "Building context...". Once that's done, ask your question in plain language, for example "summarize this PDF" or "what's the total in this spreadsheet?"
{% hint style="success" %}
Your uploads are automatically scanned for viruses before they're stored, so you can attach files with peace of mind.
{% endhint %}
### Importing from Google Drive
You can also bring files in from Google Drive. This is offered through a chat **folder's** Files panel, which has both **Upload** and **Import from Drive** options, rather than from the main message box. Files you bring in from Drive show up as previews in the composer and are downloaded and indexed when you send the message.
The first time you use it, you may be asked to connect Google Drive and grant access.
{% hint style="info" %}
Folder files act as shared context for every chat in that folder. To learn how folders work, see [Organizing your chats](/chatting-with-tim/organizing-chats.md). To connect Google Drive, see [Connecting your accounts](/account-and-settings/integrations.md).
{% endhint %}
If you start a new chat in the same flow, your attached files can carry over to it.
## Voice dictation
Prefer to talk instead of type? Use the microphone button (**Dictate a message**) to speak your message.
{% stepper %}
{% step %}
## Start recording
Click the microphone button. The text box is replaced by a live audio waveform so you can see that it's listening.
{% endstep %}
{% step %}
## Finish or cancel
Two controls appear:
* **Use dictated text** (or press Enter) to finish and transcribe.
* **Cancel dictation** (or press Esc) to discard the recording.
While your speech is being transcribed, the confirm button shows a spinner.
{% endstep %}
{% step %}
## Review and send
The transcribed text is **added into the message box** (after anything you'd already typed). It is **not** sent automatically, so you can read it over, edit it, and add more before you send.
{% endstep %}
{% endstepper %}
{% hint style="info" %}
Dictation follows your app language, so set your language to Dutch or English depending on how you speak. See [Profile and language](/account-and-settings/profile-and-language.md).
{% endhint %}
Dictation needs microphone permission in your browser. If you record nothing, you'll see "No speech was detected." If something goes wrong, you'll see "We couldn't transcribe that. Please try again." Both messages can be dismissed, and you can simply try again.
## Where to next
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://docs.ebrain.ai/chatting-with-tim/files-and-voice.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.