Start with a text-based PDF

A PDF needs selectable text to import directly. Scanned pages are images and need OCR in another tool first. Encrypted documents and files longer than 100 pages are not supported.

Review the extracted words

Columns, headers and tables can affect reading order. Remove page furniture, fix line breaks and spell out abbreviations where necessary. Uploads can be up to 15 MB, but a spoken take still has its own character limit.

Work through a long document

Use the long-text helper to divide extracted writing into smaller parts. Load one part into the studio, review it and generate it. Keep the settings consistent and collect your takes as a ZIP.

A STARTING POINT FOR YOUR SCRIPT
Your document can become a listening experience. Import a text-based PDF, check the reading order, choose a voice, and create your first take.

Import your PDF

Up to 15 MB. Review extracted text before synthesis. Longer text opens in the split-text helper.

Make a small test first

Choose a voice, generate a short take and listen before building a longer project. Scripts are processed by an online speech service; avoid material you should not share with an outside provider.

Open the studio ↗