Supported Languages in Video to Text

Video to Text supports 99 languages for speech transcription. You can choose a specific language, let the app detect the language automatically, or use multilingual detection when the recording switches between languages.

If you are new to the workflow, start with How to Use Video to Text. If you need file guidance first, Supported Media Formats for Video to Text covers the upload formats and limits.

How language selection works

Video to Text offers three practical language paths:

Choose a language manually if you already know the spoken language.
Use automatic language detection when the file contains one language but you are not sure which one.
Use multilingual detection when speakers switch between languages in the same file.

This setup works well for interviews, lessons, meetings, podcasts, and mixed-language recordings.

When to select a language manually

Manual selection makes sense when:

the file uses one clear language
you want a predictable setup before processing starts
you already know the source language from the recording context

If the recording includes code-switching or repeated language changes, multilingual detection is the better fit.

Supported languages list

Below is the current supported language list used for documentation content in this project.

A to D

Afrikaans (af)
Albanian (sq)
Amharic (am)
Arabic (ar)
Armenian (hy)
Assamese (as)
Australian English (en_au)
Azerbaijani (az)
Bashkir (ba)
Basque (eu)
Belarusian (be)
Bengali (bn)
Bosnian (bs)
Breton (br)
British English (en_uk)
Bulgarian (bg)
Burmese (my)
Catalan (ca)
Chinese (zh)
Croatian (hr)
Czech (cs)
Danish (da)
Dutch (nl)

E to L

Estonian (et)
Faroese (fo)
Finnish (fi)
French (fr)
Galician (gl)
German (de)
Global English (en)
Georgian (ka)
Greek (el)
Gujarati (gu)
Haitian (ht)
Hausa (ha)
Hawaiian (haw)
Hebrew (he)
Hindi (hi)
Hungarian (hu)
Icelandic (is)
Indonesian (id)
Italian (it)
Japanese (ja)
Javanese (jw)
Kannada (kn)
Kazakh (kk)
Khmer (km)
Korean (ko)
Lao (lo)
Latin (la)
Latvian (lv)
Lingala (ln)
Lithuanian (lt)
Luxembourgish (lb)

M to R

Macedonian (mk)
Malagasy (mg)
Malay (ms)
Malayalam (ml)
Maltese (mt)
Maori (mi)
Marathi (mr)
Mongolian (mn)
Nepali (ne)
Norwegian (no)
Norwegian Nynorsk (nn)
Occitan (oc)
Panjabi (pa)
Pashto (ps)
Persian (fa)
Polish (pl)
Portuguese (pt)
Romanian (ro)
Russian (ru)

S to Z

Sanskrit (sa)
Serbian (sr)
Shona (sn)
Sindhi (sd)
Sinhala (si)
Slovak (sk)
Slovenian (sl)
Somali (so)
Spanish (es)
Sundanese (su)
Swahili (sw)
Swedish (sv)
Swiss German (de_ch)
Tagalog (tl)
Tajik (tg)
Tamil (ta)
Tatar (tt)
Telugu (te)
Thai (th)
Tibetan (bo)
Turkish (tr)
Turkmen (tk)
Ukrainian (uk)
Urdu (ur)
US English (en_us)
Uzbek (uz)
Vietnamese (vi)
Welsh (cy)
Yiddish (yi)
Yoruba (yo)

Practical tips for language choice

Choose the language yourself when you know exactly what is in the file. Use automatic detection when you are unsure. Use multilingual detection when the file moves between languages and you want the transcript to follow those changes.

For meeting recordings, you can also turn on speaker labels so the exported transcript is easier to review later.

What you can export after transcription

Once transcription is complete, Video to Text supports these export formats:

csv
srt
vtt
txt

If your main goal is subtitle creation, srt and vtt are usually the first formats to try. For spreadsheets or structured review, csv is useful. For plain reading and editing, txt keeps things simple.

Supported Languages in Video to Text | 99 Languages