Supported languages and voices
Read PDFs Aloud in 55+ Languages
PageVoice turns the text already in your PDF into speech. Learn how language detection works, when to choose a language yourself, and how to get clearer results.
How PDF language selection works
PageVoice separates text extraction from language and voice selection so you can correct the result before listening.
Extract the PDF text
PageVoice first reads the text layer in your PDF. Text-based documents usually produce the cleanest paragraphs and pronunciation.
Detect when possible
When reliable language information is available, PageVoice uses it to suggest a suitable language and voice. Automatic detection is not guaranteed.
Choose or correct it
If detection is unavailable or incorrect, PageVoice asks you to select the document language. You can also change it in the reader.
PageVoice reads; it does not translate
The spoken audio follows the language already written in your document. Selecting another language changes pronunciation and voice options, but it does not translate the PDF's words.
Tips for commonly used language groups
Choose the language that best matches the document, then listen to a short section before continuing through a long PDF. Voice and accent choices vary by language and plan.
English variants
Choose the closest available English region when accent and local pronunciation matter. English (US) and English (UK), for example, can read the same text differently.
Spanish
Spanish pronunciation varies across regions. Select the closest available Spanish voice and preview names, abbreviations, and local vocabulary before a long listening session.
Portuguese
Brazilian and European Portuguese have distinct pronunciation. Match the voice to the document's intended audience when that choice is available.
French
Use the closest available French voice for the document. Proofread extracted names, numbers, and abbreviations if the source uses specialist or regional vocabulary.
German, Italian, and Dutch
Keep the document language set explicitly when borrowed English terms or technical vocabulary could make automatic detection uncertain.
South Asian languages
Hindi, Bengali, Gujarati, Kannada, Malayalam, Marathi, Punjabi, Tamil, Telugu, and Urdu work best when the PDF has a selectable Unicode text layer in the correct script.
East Asian languages
For Mandarin, Cantonese, Japanese, and Korean, select the language that matches the document rather than relying on shared characters or short text samples.
Arabic and right-to-left documents
Arabic, Hebrew, and Urdu PDFs need correctly ordered text. If extracted lines or punctuation appear out of sequence, correct the source or try a clearer, simpler PDF.
All Supported Languages
PageVoice currently supports 55 document languages. The voices and accents available within each language depend on the language and your plan.
- Afrikaans
- አማርኛAmharic
- العربيةArabic
- БългарскиBulgarian
- বাংলাBengali
- CatalàCatalan
- 普通话Mandarin Chinese
- ČeštinaCzech
- DanskDanish
- DeutschGerman
- ΕλληνικάGreek
- English
- EspañolSpanish
- EestiEstonian
- EuskaraBasque
- SuomiFinnish
- Filipino
- FrançaisFrench
- GalegoGalician
- ગુજરાતીGujarati
- עבריתHebrew
- हिन्दीHindi
- HrvatskiCroatian
- MagyarHungarian
- Bahasa IndonesiaIndonesian
- ÍslenskaIcelandic
- ItalianoItalian
- 日本語Japanese
- ಕನ್ನಡKannada
- 한국어Korean
- LietuviųLithuanian
- LatviešuLatvian
- മലയാളംMalayalam
- मराठीMarathi
- Bahasa MelayuMalay
- Norsk BokmålNorwegian Bokmål
- NederlandsDutch
- ਪੰਜਾਬੀPunjabi
- PolskiPolish
- PortuguêsPortuguese
- RomânăRomanian
- РусскийRussian
- SlovenčinaSlovak
- SlovenščinaSlovenian
- СрпскиSerbian
- SvenskaSwedish
- KiswahiliSwahili
- தமிழ்Tamil
- తెలుగుTelugu
- ไทยThai
- TürkçeTurkish
- УкраїнськаUkrainian
- اردوUrdu
- Tiếng ViệtVietnamese
- 粵語Cantonese
PDF quality affects the audio
PageVoice automatically uses OCR for scanned pages, though OCR errors can affect pronunciation. Clear scans work best; complex layouts, tables, unusual reading order, and mixed-language documents may need corrections or manual language changes.
Language and voice questions
Practical answers about detection, voice choices, scanned files, mixed-language PDFs, and translation.
Does PageVoice always detect my PDF's language?
No. PageVoice uses language information when it can determine it reliably, but automatic detection is not guaranteed. When detection is unavailable, PageVoice asks you to choose the document language manually.
Can I change the detected language?
Yes. If the suggested language is wrong, choose the correct language when prompted or change it from the reader's language controls.
Are the same voices and accents available for every language?
No. Voice models, accents, and regional variants vary by language and plan. Preview a voice with part of your document before committing to a long listening session.
Will scanned or mixed-language PDFs work?
Yes. PageVoice automatically uses OCR for scanned pages, though results depend on scan quality. Complex layouts and mixed-language documents may need text corrections or manual language changes as you listen.
Does PageVoice translate PDFs into another language?
No. PageVoice reads the existing language in your PDF aloud. Changing the selected language changes pronunciation and available voices; it does not translate the document's words.
Ready to listen to your PDF?
Upload a digital or scanned PDF, confirm its language, and preview the voice before you continue.