Choose a voice and listen: the text follows along, the paragraph currently being read is highlighted, and tapping a paragraph jumps to it. The first three pages are read aloud; if your document has more, the tool tells you and still reads.
Drag file here
AI-assisted - You review every step before it is applied
Your file is not uploaded. Only the text from the selected page is sent to the AI service, and the translation is returned.
In three steps: Read PDF aloud
- Select a PDF file or drop it here with Drag & Drop.
- Choose voice and speed, then tap “Read aloud”.
- Listen; the text follows along, and you can pause or continue anytime.
Frequently asked questions
What does it sound like?
Like a person, not a station announcement: the voices come from the OpenAI AI service and speak German with natural intonation. Choose from eleven voices, from bright and friendly to deep and calm.
Why only three pages?
Every page read aloud costs us money through the AI service. That is why each run currently covers the first three pages. Your document is still accepted: the tool reads the first three pages and tells you it has more. To hear another section, extract it with “Split PDF”; the file moves there with you, without selecting it again. More pages at once will be available in a paid version.
Is my file uploaded?
No. Your browser extracts the text; only the text from the pages being read is sent to the AI service, paragraph by paragraph. The audio is returned. The file itself stays on your device.
Does it work with scans?
Only with a text layer. For a scan, first use text recognition; the tool shows you how.