Supported transcription languages

Descript can automatically transcribe audio and video in 26 languages.

Currently, supported transcription languages are limited to those using the Latin alphabet. Languages such as Chinese, Japanese, or Russian are not yet supported, but it's certainly something we’d like to add in the future.

Available transcription languages
Brazilian Portuguese English (US) Italian Slovak
Catalan Finnish Latvian Slovenian
Croatian French (FR) Lithuanian Spanish (US)
Czech German Malay Swedish
Danish Greek (Beta) Norwegian Turkish
Dutch Hindi (Beta) Polish Welsh* (Beta)
English (UK)* Hungarian Romanian  
*must be manually selected when transcribing, not compatible with auto language detection

Set language preferences

If you work with multiple languages, you can set a preferred transcription language and/or enable Always ask before transcribing in your App settings. When enabled, Descript will prompt you to select a language before each transcription.

Re-transcribe in a different language

If the wrong language was selected during your initial transcription, you can re-transcribe the file:

  1. Click Project in the right-hand sidebar and open the Files section.
  2. Click the Ellipsis menu icon next to your file name.
  3. Select Re-transcribe.
  4. Choose the correct transcription language.
  5. Click Done to re-transcribe your file.
    Modal to select a different transcription language

Language support for editing and AI tools

Some Descript features currently support only English transcripts. If you’re using another language, note the following tools are English-only:

Inverse Text Normalization (ITN)

ITN automatically formats spoken numbers and dates (e.g., “Nineteen Forty-Five” → “1945”). Currently supported in English, French, and Spanish.

Translation and multi-language files

  • Descript supports transcription in only one language per file. Files with multiple spoken languages are not currently supported.
  • To translate your transcript into another language, see our Translate and dub speech feature suite