Which Languages Can Scriptery Transcribe?

Auto-detection, no settings required

Scriptery's transcription is powered by Whisper, an automatic speech recognition model that detects the spoken language on its own — there's no dropdown to configure before you transcribe.

Which languages are supported?

Whisper supports dozens of languages, including (but not limited to):

• English, Spanish, French, German, Italian, Portuguese
• Japanese, Korean, Mandarin Chinese, Cantonese
• Arabic, Hindi, Russian, Turkish, Vietnamese, Thai, Dutch

If a video's spoken language isn't in this list, transcription may still work with reduced accuracy, or may return unrecognizable text — try it and see.

Mixed-language and accented speech

Whisper handles moderate code-switching (a sentence with words from two languages) reasonably well, but heavily accented speech or fast cross-talk can reduce accuracy. Clean, single-speaker audio gives the best results regardless of language.

Interface language vs. transcription language

These are two separate things: Scriptery's website interface is available in multiple languages, while the transcription engine itself works across 50+ spoken languages regardless of which interface language you're browsing in.