PDF to Speech
Upload a PDF, and its text gets extracted and loaded into the editor — pick a voice, generate, download the MP3. Works on text-based PDFs (reports, articles, ebooks). It doesn't work on scanned or photographed pages, which have no extractable text layer.
No login • Up to 15 MB • 580+ voices in 75+ languages
How it works
1. Upload your PDF
Files up to 15 MB. The text layer is extracted automatically — no manual copy-paste needed.
2. Review the extracted text
It lands directly in the editor, capped at 5,000 characters per generation. Check it reads cleanly before generating.
3. Pick a voice and generate
Download the MP3, or generate the next section if your document is longer than one pass covers.
What doesn't work
- Scanned or photographed PDFs — no text layer to extract. Run these through OCR first.
- Dense tables or multi-column layouts — text often extracts out of visual order and needs manual cleanup.
- Documents over 15 MB or over 5,000 characters per generation — split large ones into sections.
More detail on all of this in our step-by-step PDF-to-audio guide.
Frequently asked questions
Why did my PDF come back empty?
It's most likely a scanned or image-based PDF with no extractable text layer. OCR it first, then upload the result.
Can I convert a whole book at once?
Each generation covers up to 5,000 characters. Longer documents need multiple passes.
What's the maximum file size?
15 MB per upload.
