Turkish audio and video to text

Special letters

Turkish uses letters such as ı (dotless i), ğ, ş, ç, ö and ü, and a missing or wrong dot changes a word. Look at these when you proof-read, and fix any in the editor.

Long words and names

Turkish builds long words by adding endings, and names and places carry endings of their own. Search the transcript for a name to check each form.

Typical uses

Lectures and seminars, interviews, business calls, and Turkish captions for video you made.

Which model works best for Turkish

Turkish is supported with a good amount of training material, but less than the largest languages, so the small model makes more slips than it does for English or Spanish, especially on rare words, names and fast or noisy speech. Expect a draft that needs a proper read-through.

On tryscriptorium.com the no-account preview and regular accounts run the small model (the larger medium and large-v3 models run when you self-host Scriptorium). In an account, pick Small in the model menu rather than Auto: Auto prefers the fastest, least accurate model for long files or a busy queue.

Turkish has a good amount of training speech; clear audio gives a usable draft on the small model. Suffix-heavy words, names, and the dotted and dotless i are what to proof-read.

Subtitles and captions in Turkish

Turkish words run long, so aim for two lines of about 37 to 42 characters and avoid splitting a word with its suffix. Check İ, ı, ğ and ş survive in the exported file; SRT and VTT are UTF-8.

The uploader is set to Turkish

The upload box on this page transcribes as Turkish, so the recogniser does not have to guess the language from the first seconds. If the recording is in another language or switches languages, use Audio to text, which detects the language automatically. Automatic transcription is a draft and no accuracy figure is promised: check names, numbers and anything you will rely on.