Skip to main content

Multilingual transcription

Multilingual transcription for recorded speech

Upload a recording in around 99 languages and get an editable, speaker-labeled transcript back. The public preview detects the language automatically, so you do not have to pick it yourself.

Common source-language options (18 entries)

English appears as Global, Australian, British, and US English. These are four recognition options within one language, not four additional languages.

More source languages

中文 · 한국어 · Polski · Русский · Українська · Afrikaans · Shqip · አማርኛ · Հայերեն · অসমীয়া · Azərbaycanca · Башҡортса · Euskara · Беларуская · বাংলা · Bosanski · Brezhoneg · Български · မြန်မာဘာသာ · Català · Hrvatski · Čeština · Eesti · Føroyskt · Galego · ქართული · Ελληνικά · ગુજરાતી · Kreyòl Ayisyen · Hausa · ʻŌlelo Hawaiʻi · Magyar · Íslenska · Bahasa Indonesia · Basa Jawa · ಕನ್ನಡ · Қазақша · ខ្មែរ · ລາວ · Latina · Latviešu · Lingála · Lietuvių · Lëtzebuergesch · Македонски · Malagasy · Bahasa Melayu · മലയാളം · Malti · Māori · मराठी · Монгол хэл · नेपाली · Norsk Nynorsk · Occitan · ਪੰਜਾਬੀ · پښتو · فارسی · Română · संस्कृतम् · Српски · ChiShona · سنڌي · සිංහල · Slovenčina · Slovenščina · Soomaali · Basa Sunda · Kiswahili · Schweizerdeutsch · Tagalog · Тоҷикӣ · தமிழ் · Татарча · తెలుగు · ไทย · བོད་སྐད་ · Türkmençe · اردو · Oʻzbekcha · Cymraeg

How multilingual transcription works

Hushscript's multilingual transcription services work with recorded speech rather than live interpretation. The public preview uses automatic detection and covers up to 5 minutes. In the full app, leave the source language on automatic or select it manually before upload. The transcript stays in the spoken language unless you optionally choose translation targets before the job starts. Timestamps, editing, all 21 export formats, and the separate password-protected .husharchive are available across supported languages. Recordings that switch languages still need review; Hushscript does not promise universal code-switching accuracy.

Speaker detection is available across the supported transcription languages. Check automatic labels against the recording and correct them in Hushscript before export.

Audio processing and privacy

For local video, the source stays on your device and only prepared audio is sent for online recognition. Audio from the EU, EEA, Switzerland, and the UK is processed in the EU. Hushscript removes its transcription-audio copy after processing and never trains on your recordings.

Source languages, translation targets, and interface locales

This page covers around 99 spoken source languages. Written translation is optional in the full app: choose from 13 target languages before transcription, and each target adds 25% of the recording's duration to billed minutes. Jobs with translation targets use personal minutes rather than a Teams pool. The website and app interface currently support 12 locales.

Start multilingual transcription in the app

Preview up to 5 minutes before you create an account, and a new personal account gets a free preview of its first upload in the app. Full transcription needs an account and minutes; eligible personal accounts get 30 free minutes once, after card verification or with a first purchase. No subscription.

Get 30 free minutes