Free Serbian Speech-to-Text

Serbian is spoken by around 9 million people and is the official language of Serbia. It is unusual among European languages for being fully digraphic: it is written in both Cyrillic and Latin, and every Serbian text can be transliterated one-to-one between the two scripts. Standard Serbian mostly follows the ekavian pronunciation, so lek and mleko rather than the ijekavian lijek and mlijeko.

ConvertSpeech transcribes it automatically. Upload your audio or video and our speech-recognition engine writes out the spoken Serbian with punctuation, ready to copy into a document, subtitle file or translation tool. It runs in your browser, needs no installation, and your first minutes are free with no account required.

Serbian's defining feature for transcription is its dual script. Speech carries no script of its own, so the engine transcribes the spoken Serbian into one written form — and because Cyrillic and Latin map letter-for-letter in Serbian, you can convert the result to the other script without changing a single word. The ekavian forms of standard Serbian are reflected directly in the output.

Serbian, Croatian and Bosnian are closely related, so selecting Serbian specifically gives you the ekavian conventions and the option to work in Cyrillic. As always, the largest factor in accuracy is recording quality — a clear signal with little background noise beats everything else.