Malay audio and video to text

Malaysian, Singaporean and Bruneian Malay

Standard Malay (Bahasa Melayu) is spoken in Malaysia, Brunei and Singapore, with regional accents such as Kelantan, Terengganu and Sabah that can sound very different. Colloquial speech, often called bahasa pasar or rojak when mixed with English, is harder than newsreader Malay. Indonesian is closely related; if your speaker is Indonesian, use the Indonesian page.

Spelling, loanwords and script

Malay today is written in the Latin alphabet (Rumi), and that is the form you get back. Spelling is regular, but short forms, English loanwords and brand names are written inconsistently, and words like tak and tidak may switch between casual and formal. Names and place names from Arabic, Chinese or Tamil origins are the usual corrections.

What speakers of Malay use it for

Recorded lectures at universities in Malaysia and Brunei, meeting notes at companies that work in Malay, interviews and community radio, sermons and talks, and captions for videos on YouTube and TikTok. Reporters also turn press conferences into quotable text, which is quicker than typing from the recording.

Which model works best for Malay

Malay is a lower-resource language for Whisper-family models, and the small model is noticeably less reliable here than for the major languages. Use clear, single-speaker audio, keep clips short, and plan to edit a good deal. For the best result, self-hosting with large-v3 helps.

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.

Malay is a weaker language for the small model and mixed Malay and English is harder still. Use clean single-speaker audio, shorter clips, and proofread names and English phrases. For long or formal material, self-host with large-v3 for a more reliable draft.

Subtitles and captions in Malay

Malay subtitles use ordinary word spaces, so break lines at phrase boundaries and keep them to about 35 to 42 characters. In mixed Malay and English video, check that the English phrases are spelled correctly. SRT and VTT are UTF-8, so every accent in names and loanwords displays correctly in VLC and YouTube.

The uploader is set to Malay

The upload box on this page transcribes as Malay, 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.