How do I import a PDF, DOCX, or audio file?

On documented Windows builds, the Import button brings existing documents, images or audio into VoicePad. You can then review the extracted text and process it with local AI Tools.


Choose the file type

  • TXT: loads the existing text.
  • DOCX: extracts text from a Word document.
  • PDF: extracts text and offers a preview before loading.
  • PNG or JPG: uses OCR to recognise text in an image.
  • WAV, MP3 or M4A: transcribes speech using Whisper.

Import and review

  1. Click the paperclip Import button in the footer.
  2. Select your file.
  3. Review any preview. If offered, choose Load to replace the current transcript or Append to add to it.
  4. Check names, numbers and formatting in the resulting text.
  5. Copy or save the reviewed result.

Use AI Tools afterwards

Try Summary for a long recording, Improve for a draft or Translate for a document. These desktop tools require Ollama and an installed local model. File import and dictation do not require a cloud transcription service.

If the result is incomplete

Complex PDF layouts and low-quality images can produce extraction errors. Compare the imported text with the original before relying on it, especially for tables, dates and amounts.


More platform-specific guidance: VoicePad Help Center.