How do I import a PDF, DOCX, or audio file?
The **Import button (📎)** in VoicePad's footer brings any document into the app for AI processing — not just dictation.
**Windows only feature.** Tap the paperclip icon in the footer bar.
**Supported file types:**
| File type | What VoicePad does |
|-----------|---------------------|
| `.txt` | Loads text directly into the transcript area |
| `.docx` | Extracts text, loads into transcript area |
| `.pdf` | Extracts text, shows preview dialog before loading |
| `.png`, `.jpg`, `.jpeg` | OCR (optical character recognition) extracts text |
| `.wav`, `.mp3`, `.m4a` | Whisper transcribes the audio, result added to history |
**The workflow:**
1. Click 📎 in the footer bar
2. Select your file
3. For PDFs: a preview dialog shows the extracted text — choose Load (replace transcript) or Append (add after existing text)
4. The text appears in the transcript area
5. Now run AI Tools on it — Clean, Improve, Summary, Translate — all locally, no cloud
**Practical examples:**
- **Imported a meeting audio recording?** Whisper transcribes it. Then run Summary to get key points and action items.
- **Got a PDF article you need translated?** Import → Translate → done.
- **Need to rewrite a draft document?** Import the DOCX → Improve.
- **Scanned receipt or photo of notes?** Import the image → OCR extracts the text.
**Parallel processing for long documents:**
For texts over 400 words, VoicePad splits the text into chunks and processes them simultaneously with up to 3 parallel workers — handling 10,000+ words at professional speed. Cancellable at any time.
For more on AI Tools, see [How do I use the AI Tools?](#).