VoxSail Docs

Supported Files and Languages

Supported video formats:

2026-07-07 2 min readGetting StartedSupported Files and LanguagesVideo filesAudio files

Video files

Supported video formats:

Video files used for Audio and Video Translation or Subtitle Transcription must meet the following limits:

Free users:

Subscribed users:

  • MP4
  • MOV
  • AVI
  • MKV
  • File size up to 200 MB.
  • Duration up to 10 minutes.
  • File size up to 500 MB.
  • Duration up to 60 minutes.

Audio files

Supported audio formats:

Audio files used for Audio and Video Translation or Subtitle Transcription must meet the following limits:

Free users:

Subscribed users:

  • mp3
  • wav
  • flac
  • m4a
  • File size up to 200 MB.
  • Duration up to 10 minutes.
  • File size up to 500 MB.
  • Duration up to 60 minutes.

Voice cloning materials

Voice cloning supports video or audio materials in the formats listed above. Voice cloning audio must be 10 to 80 seconds long and no larger than 30 MB.

Text and documents

Text Voiceover supports typed or pasted text, and can also extract text from uploaded documents. The page will show the currently supported document formats and text length limits when you upload or submit.

Supported languages

Voxsail supports recognition, translation, and voice generation for most major global languages.

The following 99 original languages can be recognized:

Afrikaans, Amharic, Arabic, Armenian, Assamese, Asturian, Azerbaijani, Belarusian, Bengali, Bosnian, Bulgarian, Burmese, Cantonese, Catalan, Cebuano, Chichewa, Croatian, Czech, Danish, Dutch, English, Estonian, Filipino, Finnish, French, Fula, Galician, Ganda, Georgian, German, Greek, Gujarati, Hausa, Hebrew, Hindi, Hungarian, Icelandic, Igbo, Indonesian, Irish, Italian, Japanese, Javanese, Kabuverdianu, Kannada, Kazakh, Khmer, Korean, Kurdish, Kyrgyz, Lao, Latvian, Lingala, Lithuanian, Luo, Luxembourgish, Macedonian, Malay, Malayalam, Maltese, Chinese/Mandarin, Maori, Marathi, Mongolian, Nepali, Northern Sotho, Norwegian, Occitan, Odia, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Serbian, Shona, Sindhi, Slovak, Slovenian, Somali, Spanish, Swahili, Swedish, Tamil, Tajik, Telugu, Thai, Turkish, Ukrainian, Umbundu, Urdu, Uzbek, Vietnamese, Welsh, Wolof, Xhosa, Zulu

The following 83 target languages support translation and dubbing:

English, Chinese/Mandarin, Japanese, Korean, Spanish, Portuguese, Arabic, Russian, French, German, Swedish, Italian, Turkish, Norwegian, Dutch, Welsh, Basque, Catalan, Danish, Galician, Tamil, Hungarian, Finnish, Polish, Estonian, Hindi, Latin, Urdu, Thai, Vietnamese, Javanese, Bengali, Yoruba, South Slavic, Czech, Swahili, Nynorsk, Hebrew, Malay, Ukrainian, Indonesian, Kazakh, Bulgarian, Latvian, Burmese, Tagalog/Filipino, Slovak, Nepali, Persian, Afrikaans, Greek, Tibetan, Croatian, Romanian, Shona, Maori, Yiddish, Amharic, Belarusian, Khmer, Icelandic, Azerbaijani, Sindhi, Breton, Albanian, Pashto, Mongolian, Haitian Creole, Malayalam, Serbian, Sanskrit, Telugu, Georgian, Bosnian, Punjabi, Lithuanian, Kannada, Sinhala, Armenian, Marathi, Assamese, Gujarati, Faroese

The original language can be set to auto-detect by default. You can also select the original language manually before submission. The target language must be selected or confirmed.

Next stepOpen related feature
Continue

Related docs

Feature LimitsAudio and Video Translation