PDF to audio
Listen to your PDFs with natural Kokoro voices.
AUDIO TOOL
SMALL TOOLS. EVERYDAY SUPERPOWERS.
Free audio tools
Listen to PDF text, generate English speech or transcribe English audio to a PDF. Kokoro and Whisper run on your device after model downloads.
No uploadsNo account needed
Audio tools
3 toolsAudio tools
3 toolsListen to documents. Turn recordings into text.
Which speech tool should I choose?
PDF to audio reads selectable PDF text aloud with Kokoro. Text to audio turns typed text into a WAV recording with Kokoro. Audio to PDF uses Whisper to transcribe a recording, then lets you review the text before exporting a PDF. These tools currently support English speech.
Are recordings or text sent to an AI service?
Speech generation and recognition run locally in your browser. Your files and text are not sent to an AI inference service. The first use still requires internet access to download model and runtime files; optional models may be cached by your browser.
How much audio or text can I process?
Audio to PDF accepts a browser-decodable recording up to 30 MB and 10 minutes long. Kokoro speech generation accepts up to 12,000 characters, including extracted PDF text. PDF to audio accepts PDFs up to 150 MB and does not include OCR for scanned pages.
Do I need to review the transcript?
Yes. Whisper recognition can make mistakes, especially with noise or unfamiliar names. Edit the transcript before exporting. The PDF export supports Latin text. Processing speed and model availability depend on your browser, memory and device.
xfiles is operated by Nihal Gupta. Read the Privacy Policy and Terms of Service, or contact the operator with questions.
Tool directories
+25 moreShow fewer
