2 voices · Northern (Hanoi) · Southern (Saigon) · 48 kHz
Vietnamese text to speech
Two Vietnamese voices, one from each end of the country: a gentle Northern presenter from Hanoi and an easy-going Southern radio voice from Saigon. Paste your script with full tone marks and hear it read with the accent your audience expects. Both read standard Unicode Vietnamese exactly as you type it.
Listen
Every Vietnamese voice
Linh
Female · young adult · Northern (Hanoi)
“Xin chào quý vị. Hà Nội những ngày cuối thu, trời se lạnh, hoa sữa nồng nàn trên khắp các con phố cổ.”
Good evening, everyone. In Hanoi’s last days of autumn the air turns chilly, and the scent of milkwood flowers fills the streets of the Old Quarter.
- television
- presenter
- gentle
Minh
Male · adult · Southern (Saigon)
“Chào mấy bạn nha! Sáng nay Sài Gòn nắng đẹp quá trời, ghé quán cà phê sữa đá quen thuộc rồi mình nói chuyện tiếp nè.”
Hey everyone! Saigon is so sunny and lovely this morning. Let me stop by my usual iced-coffee place, and then we’ll keep chatting.
- radio
- conversational
- laid-back
About Vietnamese in Voxmint
Northern and Southern Vietnamese differ in more than accent. Tones are realised differently, some consonants merge in the South, and everyday vocabulary changes too. Linh speaks the Hanoi Vietnamese heard on national television, soft and precise. Minh speaks Southern Vietnamese from Saigon, relaxed and friendly, with the “nha” and “nè” that make Southern speech sound so warm.
Tone marks are not optional. Vietnamese has six tones, and the diacritics are what tell the voice which one to use; “ma”, “má”, “mà”, “mả”, “mã” and “mạ” are six different words. Always paste your script with full diacritics, in Unicode as any modern keyboard produces it. Text without tone marks, the way people sometimes type in chat, cannot be read correctly by a person or a voice.
On everyday sentences the tones come out right, but a synthetic voice can occasionally flatten or confuse a tone, especially on rare words and names. If a word sounds wrong, try a fresh take or rephrase the sentence slightly; listen to anything important before you publish it. Match vocabulary to the voice as well: Southern words like “ly” for glass or “bông” for flower sound natural from Minh but odd from a Hanoi voice.
Write numbers, dates and currency as you want them spoken, for example “mười lăm tháng ba” instead of 15/3 and “năm mươi nghìn đồng” in a voice-over. Commas and full stops control the pacing, and short sentences give the most natural rhythm.
Choosing between the two is mostly about audience. Linh’s Hanoi voice is the safe choice for national campaigns, e-learning and formal communication, because Northern Vietnamese is the broadcast standard across the country. Minh is the better choice when you speak directly to people in the South, in social video, food content or a friendly brand voice. For a Central accent, or a younger or older speaker, describe the voice you need in the studio and keep the best take.
Design or clone a Vietnamese voice
Describe the voice you want, for example:
A cheerful young woman from Da Nang in her twenties with a bright, clear voice and a lively pace, like the host of a travel vlog.
Or clone one from a few seconds of your own recording.
Use cases
What people make with Vietnamese voices
Social video and TikTok
Minh’s friendly Southern delivery suits short videos, food reviews and vlogs aimed at viewers in Ho Chi Minh City and the South.
News and corporate video
Linh’s calm Northern presentation fits news summaries, company videos and public announcements.
E-learning
Clear diction in both accents makes these voices useful for courses, onboarding material and Vietnamese lessons for learners.
Advertising and brand voice
Pick Linh for a polished national campaign or Minh for a warmer Southern feel, and keep the same voice across every ad in the series.
Help lines and notifications
Clear diction and full tones make both voices easy to follow in IVR menus, delivery notifications and help-centre videos.
Audiobooks and short stories
Linh’s soft, precise delivery suits short stories, poetry and audiobook chapters for Vietnamese listeners.
Questions
- Northern or Southern: which accent should I use?
- Use the one your audience lives with. Northern Vietnamese is standard on national television; Southern Vietnamese feels more local and friendly to audiences in the South.
- Do I need tone marks?
- Yes. Without diacritics a Vietnamese word is ambiguous, so paste your script with full tone marks for a correct read.
- Can it do a Central accent, like Hue or Da Nang?
- There is no ready-made Central voice yet. You can describe one in the studio, but results vary, so compare several takes.
- Can I clone a Vietnamese voice?
- Yes. Upload or record a few seconds of clear speech in your own voice, or in a voice you have permission to use, and new lines will be spoken in that timbre. Adding the transcript of the clip gives the closest match.
- Does it handle Vietnamese names and places?
- Common names and place names written with full tone marks read correctly. For unusual names, listen to a take first and rephrase or re-render if a tone sounds off.
- Can I use Southern vocabulary with the Hanoi voice?
- You can, but it will sound a little unusual, as it would from a real Hanoi speaker. Match the vocabulary to the voice: Southern words with Minh, Northern words with Linh.