Transcribe Video to Text
Transcripts in 100 languages, with speakers and timestamps — made on your device, never uploaded.
Free · No upload · No sign-up · No watermark
How to transcribe a video to text
- 01
Open a video
Drop an MP4, MOV, MKV or almost any other video. The language is detected by itself.
- 02
Transcribe on your device
Speech recognition runs in your browser. The text appears as it's recognised, in paragraphs with their times.
- 03
Edit and download
Identify and name the speakers, translate it to English, fix any word — then download it as Word, PDF, TXT or SRT.
Why use Cutlia for this
Who said what
Speakers are told apart by their voices. Name one once and “Speaker 1” becomes “Maya” everywhere.
Read along
Click any word to jump to that moment in the video. While it plays, the word being spoken lights up.
Search and correct
Find a name in an hour-long recording, fix it everywhere at once, and undo any change.
Word, PDF and subtitles
Download a Word document, a PDF, plain text or Markdown — or SRT and VTT subtitles, split by speaker. PDFs are right in every script: Arabic and Hebrew right to left, Chinese, Japanese, Korean, Hindi, Thai.
English translation
Get an English version next to the original, from speech in any of 100 languages.
Private, and kept for you
Nothing is uploaded. Your recent transcripts stay in this browser, so you can come back and carry on.
Captions on your video
One click turns the transcript into captions on the video in Auto Subtitles — your fixes kept, nothing transcribed again.
Works in 100 languages
The spoken language is detected by itself, and speech in any of them can be turned into English. Accuracy is best in the most widely spoken ones.
- English
- Chinese · 中文
- German · Deutsch
- Spanish · Español
- Russian · Русский
- Korean · 한국어
- French · Français
- Japanese · 日本語
- Portuguese · Português
- Turkish · Türkçe
- Polish · Polski
- Catalan · Català
- Dutch · Nederlands
- Arabic · العربية
- Swedish · Svenska
- Italian · Italiano
All 100 languages
- Afrikaans
- Albanian · Shqip
- Amharic · አማርኛ
- Arabic · العربية
- Armenian · Հայերեն
- Assamese · অসমীয়া
- Azerbaijani · Azərbaycan
- Bangla · বাংলা
- Bashkir · Башҡорт
- Basque · Euskara
- Belarusian · Беларуская
- Bosnian · Bosanski
- Breton · Brezhoneg
- Bulgarian · Български
- Burmese · မြန်မာ
- Cantonese · 粵語
- Catalan · Català
- Chinese · 中文
- Croatian · Hrvatski
- Czech · Čeština
- Danish · Dansk
- Dutch · Nederlands
- English
- Estonian · Eesti
- Faroese · Føroyskt
- Filipino
- Finnish · Suomi
- French · Français
- Galician · Galego
- Georgian · Ქართული
- German · Deutsch
- Greek · Ελληνικά
- Gujarati · ગુજરાતી
- Haitian Creole
- Hausa
- Hawaiian · ʻŌlelo Hawaiʻi
- Hebrew · עברית
- Hindi · हिन्दी
- Hungarian · Magyar
- Icelandic · Íslenska
- Indonesian · Indonesia
- Italian · Italiano
- Japanese · 日本語
- Javanese · Jawa
- Kannada · ಕನ್ನಡ
- Kazakh · Қазақ тілі
- Khmer · ខ្មែរ
- Korean · 한국어
- Lao · ລາວ
- Latin
- Latvian · Latviešu
- Lingala · Lingála
- Lithuanian · Lietuvių
- Luxembourgish · Lëtzebuergesch
- Macedonian · Македонски
- Malagasy
- Malay · Melayu
- Malayalam · മലയാളം
- Maltese · Malti
- Māori
- Marathi · मराठी
- Mongolian · Монгол
- Nepali · नेपाली
- Norwegian · Norsk
- Norwegian Nynorsk · Norsk nynorsk
- Occitan
- Pashto · پښتو
- Persian · فارسی
- Polish · Polski
- Portuguese · Português
- Punjabi · ਪੰਜਾਬੀ
- Romanian · Română
- Russian · Русский
- Sanskrit · संस्कृत भाषा
- Serbian · Српски
- Shona · ChiShona
- Sindhi · سنڌي
- Sinhala · සිංහල
- Slovak · Slovenčina
- Slovenian · Slovenščina
- Somali · Soomaali
- Spanish · Español
- Sundanese · Basa Sunda
- Swahili · Kiswahili
- Swedish · Svenska
- Tajik · Тоҷикӣ
- Tamil · தமிழ்
- Tatar · Татар
- Telugu · తెలుగు
- Thai · ไทย
- Tibetan · བོད་སྐད་
- Turkish · Türkçe
- Turkmen · Türkmen dili
- Ukrainian · Українська
- Urdu · اردو
- Uzbek · O‘zbek
- Vietnamese · Tiếng Việt
- Welsh · Cymraeg
- Yiddish · ייִדיש
- Yoruba · Èdè Yorùbá
Frequently asked questions
Is my video uploaded to a server?
No. Cutlia processes your video directly in your browser using WebAssembly and your device's hardware. The file never leaves your computer or phone, so it stays completely private.
Can it tell who is speaking?
Yes. Click “Identify speakers” once the transcript is ready, and each paragraph is labelled with its speaker, recognised by voice. It works best when people take turns. You can rename speakers, merge two that are the same person, or change who says a paragraph.
Which languages does it understand?
100 languages, including English, Spanish, German, French, Croatian, Chinese and Arabic — all of them are listed on this page. The language is detected automatically — there's nothing to choose — and if the start is hard to tell, you're asked. Picked the wrong one? Change it anytime. Accuracy is best in the most widely spoken languages. Serbian, Bosnian and Uzbek can be written in Cyrillic or Latin, Chinese in Simplified or Traditional characters.
Why does the first video take longer?
The first time, your browser prepares speech recognition — a one-time setup that it keeps for next time. After that, transcribing starts in seconds.
Is it really free?
Yes. Cutlia is free to use with no account, no trial and no watermark on your export. The site is paid for by the ads on it, and your files never leave your device.
Popular uses
Each one is this tool, set up for the job — and it still opens any video or audio file.