Get started

Uploads & Voice Input

Attach files and use your voice to describe what you want to build

File attachments

You can upload files directly in the chat when creating or refining your app. This is useful for sharing design references, content, or any material that helps the AI understand what you're looking for.

How to upload

  1. Click the paperclip icon in the chat input area
  2. Select one or more files from your device
  3. Each file appears as an attachment card showing:
    • A thumbnail preview (for images) or file icon
    • File name and size
    • Upload status — Pending, Uploading, or a green checkmark when done
  4. Add your message describing what to do with the files, then send

You can remove any attachment before sending by clicking the X on its card.

Tip: You can upload multiple files at once. A progress indicator shows which file is currently uploading.

Supported file types

You can upload:

  • Images — JPG, PNG, GIF, WebP, SVG
  • Documents — PDF, TXT, DOC
  • Videos — MP4, WebM, MOV
  • Code files — any text-based source code

Executable files (.exe, .bat, .sh, .cmd, etc.) are blocked for security reasons.

How attachments are used

The AI uses your attachments as context when generating or refining your app. Here are some effective ways to use them:

Design references

Upload a screenshot or image of a design you like, and describe what to take from it:

"Make the hero section look similar to this screenshot —
same layout with a large heading on the left and
an image on the right."

Content & assets

Upload images you want included in your app:

"Use this logo in the header and this photo as the
hero background image."

Documents & specifications

Upload a PDF or text file with detailed requirements:

"Here's a document with all the product descriptions
and pricing. Create product cards using this content."

Tip: Be specific about how you want attachments used. Instead of just uploading an image, tell the AI exactly where and how to use it.

Voice input

Prefer talking over typing? You can describe what you want using your voice. Pentoggle will transcribe your words and add them to the chat input.

How to use voice input

  1. Click the microphone icon in the chat input area
  2. Your browser may ask for microphone permission — allow it
  3. Start speaking. A timer shows how long you've been recording
  4. Click the stop button (pulsing square icon) when you're done
  5. Wait a moment while your audio is transcribed
  6. The transcribed text appears in the input field — review and edit if needed, then send

Voice input requires a browser that supports the Web Audio API. Most modern browsers (Chrome, Firefox, Safari, Edge) support it.