Skip to content

Vietnamese transcription

Vietnamese audio and video to text

Upload Vietnamese audio or video and get a timestamped transcript with tone marks. Vietnamese is tonal and the marks change the word, so a wrong mark is a real error, not a typo. Proofread names and short, fast phrases, where the model has the least context to choose the right tone.

Free preview: one file up to 15 minutes and 25 MB, 3 tries a day, no account needed.

Want to keep your transcripts? Create a free account

Northern, Central and Southern speech

Vietnamese has three broad dialect regions: Hanoi in the north, Hue and the central coast, and Ho Chi Minh City in the south. Northern and Southern speech usually do better. Central accents are harder, with different tones and vocabulary. Some tones merge in southern speech, which can make the written tone marks less reliable. Overseas Vietnamese speakers who mix in English also add errors.

Tone marks and spacing

Vietnamese uses the Latin alphabet with many diacritics, such as ă, â, ê, ô, ơ, ư and five tone marks. Spaces separate syllables, not words, so a two-syllable word like sinh viên looks like two words. A single wrong tone can turn one word into another, so read the transcript, not only skim it.

What speakers of Vietnamese use it for

Recorded lectures and online classes, livestream and short-video captions, interviews and podcasts, and voice messages saved from messaging apps such as Zalo. Business owners also transcribe calls and meetings for notes. Searching a transcript for a name, a figure or a date is much faster than listening to the whole recording again.

Which model works best for Vietnamese

Vietnamese 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.

Vietnamese has less training data behind it than the biggest languages, so the small model makes more tone and word mistakes, especially with noise or regional accents. Keep clips short, one speaker at a time, and proofread names. Self-hosting with large-v3 usually gives better results.

Subtitles and captions in Vietnamese

Vietnamese subtitles are commonly kept to about 35 to 42 characters per line, broken between words, never in the middle of a syllable. Check tone marks on the first line of each clip, since viewers notice them. SRT and VTT export as UTF-8, so every diacritic displays correctly in VLC, YouTube and mobile editors.

The uploader is set to Vietnamese

The upload box on this page transcribes as Vietnamese, 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.

How it works

  1. Add a recording

    Drop in a video or audio file, choose one from your device, or record from the microphone. Nothing to install.

  2. It transcribes

    Speech becomes timestamped text, with speaker labels when more than one person talks.

  3. Read, fix, export

    Click any line to correct it, then download TXT, subtitles, Markdown, JSON or CSV.

Questions

Will the transcript include all the tone marks and diacritics?
Yes, it writes full Vietnamese with diacritics. Some tone marks may be wrong, since several words sound close. Read the lines that matter and fix them in the editor.
Does it work with southern and central accents?
Yes, but quality varies. Northern and Southern speech tends to work better than strong Central accents. Recording close to the speaker with little noise helps more than choosing a setting.
Can I transcribe a voice message from a chat app?
Yes, if you can save it as an audio file and upload it. See voice note to text, which applies to any saved voice message.
Which file types can I upload?
Video: MP4, MOV, MKV, WebM, AVI, M4V, WMV, FLV, MPEG, 3GP, TS. Audio: MP3, WAV, M4A, AAC, FLAC, OGG, Opus, WMA, AIFF, AMR, CAF. Anything else the server can decode as audio or video generally works too; there is no need to convert first.
Is it free?
Yes — one file up to 15 minutes and 25 MB with no account, up to 3 tries a day. A free account keeps your transcripts in a library and lifts the guest limits; the current limits and paid plans are on the pricing page.

Want your transcripts saved and longer files? Create a free account · See pricing · All use cases

Try it with your file

No account needed for a first transcript.