Speech to text · Tiếng Việt

Vietnamese audio to text, free

Upload a voice note, a call recording or a video and get Vietnamese text back. It is free for files up to 2 minutes without an account (3 files a day); longer files need a free account. Download the result as text, Word or subtitles. The transcript comes back with full tone marks (đơn hàng, chưa thấy), and an English translation is one tab away.

MP3, M4A, WAV, WhatsApp .opus, MP4 · up to 2 min free

Upload a voice note, call recording or video in Vietnamese, or record yourself. Free up to 2 minutes a file, 3 files a day, no account.

Valmiki STT

Your transcript appears here, exactly as Valmiki returns it.

Upload MP3, M4A, WAV, AAC, FLAC, AMR, a WhatsApp voice note (.opus or .ogg) or an MP4 or MOV video, or record up to 2 minutes from your microphone. Switch between Vietnamese and an English translation (made by Vyas, our language model, when you open the tab), then copy the text or download TXT or DOCX, plus SRT subtitles for uploaded files. No account needed for files up to 2 minutes, 3 a day.

Vietnamese audio to text converter

Drop in an audio or video file and get Vietnamese text back with full tone marks. It reads MP3, M4A, WAV, AAC, FLAC and AMR audio, WhatsApp voice notes (.opus and .ogg) and MP4 or MOV video, and the file is decoded on our server, so it works the same on an iPhone. You can also record from your microphone. There is no language menu: Valmiki STT, the speech recognition model behind it, works out that the speech is Vietnamese, including English words in the middle of a sentence.

Free Vietnamese speech to text: what you get

Files up to 2 minutes, 3 a day on each device, with no account.
With a free account, files up to 10 minutes and 10 MB each in the dashboard or the API, billed by the second.
The transcript in Vietnamese, and translated into English.
Copy the text or download plain text (TXT) or Word (DOCX), and subtitles (SRT) for uploaded files.

Vietnamese voice to text, saved as text, Word or subtitles

Copy the transcript, or download it as a TXT file or a Word document. For an uploaded file you also get an SRT subtitle file to load into YouTube Studio or a video editor. Long recordings after sign-up cost $0.00525 per minute of audio, billed by the second, the same for every language.

Real transcripts

What Valmiki STT returned for Vietnamese.

Each sentence was read by Liz, a Pāṇini TTS voice, and sent to Valmiki STT as a file: twice as the clean recording and twice as an 8 kHz phone-quality copy (squeezed down to 8 kHz and back, the way a phone line does it). The transcripts are shown exactly as they came back, errors included. Tested 25 October 2026. These are synthetic clips, not recorded calls.

Clean recordingReal output, 25 October 2026

What was said: Alo, cho mình hỏi đơn hàng của mình bao giờ giao vậy? Mình đặt từ thứ Hai mà tới giờ vẫn chưa thấy.; Hello, can I ask when my order will be delivered? I ordered on Monday and it still hasn't shown up.
What Valmiki STT returned, unedited: Alo, cho mình hỏi đơn hàng của mình bao giờ giao vậy? Mình đặt từ thứ hai mà tới giờ vẫn chưa thấy.

Same transcript in both clean runs: word for word with every tone mark, except thứ Hai written with a small h.

Phone quality (8 kHz)Real output, 25 October 2026

What was said: Alo, cho mình hỏi đơn hàng của mình bao giờ giao vậy? Mình đặt từ thứ Hai mà tới giờ vẫn chưa thấy.; Hello, can I ask when my order will be delivered? I ordered on Monday and it still hasn't shown up.
What Valmiki STT returned, unedited: Alo, chòm nhẵn ơi, đơn hàng của mình bao giờ giao vậy? Mình đặt từ thứ hai mà tới giờ vẫn chưa thấy.

One of two phone-quality runs, shown because it went wrong: cho mình hỏi (can I ask) became the meaningless chòm nhẵn ơi. The other phone-quality run wrote không biết (I wonder) there instead.

How to judge the accuracy yourself

No public benchmark includes Valmiki STT, so we do not publish a table comparing it with other services. Judge it on audio like yours instead. Play each clip above and compare what was said with what came back, word by word. Then upload a recording of your own that is close to what you will really transcribe: the same kind of phone line or microphone, the same speakers, the same mix of Vietnamese and English. Count the words that changed meaning, not the spelling variants, and try the 8 kHz case if your audio comes from calls.

About Vietnamese

How Vietnamese speech comes out as text.

Vietnamese is tonal, and its Latin script marks every tone: a transcript without the marks, or with the wrong ones, is a different set of words. On the clean recording, Valmiki STT returned our sentence word for word in both runs, with every tone mark in place (đơn hàng, giao vậy, chưa thấy).

The 8 kHz phone-quality copy was harder. In both phone-quality runs the rest of the sentence was right, but the short, quick phrase cho mình hỏi (can I ask) was lost: one run wrote the meaningless chòm nhẵn ơi, the other the plausible but different không biết. The voice reading our sample, Liz, is not a native Vietnamese voice, which may have made it harder; test recordings of real speakers.

Transcript script: Vietnamese (Chữ Quốc ngữ) with full tone marks. The language is already written in Latin letters, so there is no separate Roman script view.
Language setting: None. Valmiki STT detects the spoken language, including switches mid-sentence.
Price after the free files: $0.00525 per minute of audio, billed by the second.
In local currency: About 136 ₫ a minute (8,132 ₫ an hour of audio), at exchange rates from open.er-api.com, 25 October 2026.
Files: MP3, M4A, WAV, AAC, FLAC, AMR, WhatsApp .opus and .ogg, and MP4 or MOV video in the uploader. The API takes WAV, MP3, FLAC, OGG, Opus, WebM, AAC and M4A files up to 10 MB and 10 minutes.

Dialects and mixing

Northern, Central and Southern Vietnamese.

Hà Nội and Sài Gòn Vietnamese differ in pronunciation (the Southern merging of some initial consonants and the hỏi and ngã tones) and in words, such as nghìn and ngàn for thousand or bát and chén for bowl. Central speech from Huế and Nghệ An is harder still for outsiders. Valmiki STT has one Vietnamese language. Our sample is neutral and was read by a non-native voice, so test recordings from your own region.

Vietnamese customer speech mixes in English shopping words (voucher, freeship, COD, ship) and some Vietnamese spell them the Vietnamese way. We did not test English words inside Vietnamese, so check a recording with the terms your customers use.

Use cases

What people turn into Vietnamese text.

WhatsApp voice notes to Vietnamese text

Voice messages from WhatsApp, and voice notes saved from other apps as audio files. Upload the file and read the Vietnamese, or open the English tab for a colleague who does not speak it.

YouTube videos to Vietnamese text

Vietnamese vlogs, reviews, cooking and study channels. For your own channel, download the MP4 from YouTube Studio and use the SRT file as a start on Vietnamese subtitles.

Interviews and meetings

Interviews and meetings with Vietnamese suppliers, staff or research participants. Upload parts of up to 10 minutes after a free sign-up and download a Word file.

Call recordings

Delivery and order calls, like the one in our sample, for shops and logistics teams. Read what each customer asked, and check short phrases on phone-quality audio.

Voice typing

How to voice-type in Vietnamese.

Voice typing is a different job from transcribing a file: you speak and the words appear as you go. Sonex Labs has no voice-typing keyboard or app, so for that, use the tools already on your phone or computer.

1. Android phone (Gboard)
Install Gboard, add Tiếng Việt under Languages in its settings, then tap the microphone on the keyboard and speak.
2. iPhone
Add the Vietnamese keyboard in Settings, then General, Keyboard, Keyboards. If your iPhone offers dictation for Vietnamese, a microphone key appears on that keyboard.
3. WhatsApp
To type a message by voice, tap the microphone on your keyboard, not the voice-note button in WhatsApp; the keyboard writes the words into the chat box. WhatsApp can also show a transcript under a received voice message in some languages (Settings, then Chats, then Voice message transcripts). If Vietnamese is not offered there, save the voice note and upload it above.
4. Microsoft Word
Word's Dictate lists Vietnamese as a preview language, which Microsoft says may be less accurate and add less punctuation. Google Docs voice typing also lists Vietnamese.
5. Windows
Windows 11 voice typing lists Vietnamese. Switch the keyboard input to Vietnamese (Windows key + Space), press Windows key + H in a text box and speak.

For recordings longer than a minute, use the uploader above.

API

Vietnamese speech to text API.

Send a recording to POST /v1/transcribe and read the Vietnamese text from the reply. There is no language parameter. $0.00525 per minute of audio, billed by the second.

transcribe.py

1# pip install requests
2import requests
3
4with open("vietnamese-call.wav", "rb") as audio:
5    r = requests.post(
6        "https://api.sonexlabs.com/v1/transcribe",
7        headers={
8            "Authorization": "Bearer YOUR_API_KEY",
9            "Content-Type": "audio/wav",   # audio/mpeg, audio/ogg (WhatsApp notes), audio/mp4 ...
10        },
11        data=audio,
12    )
13r.raise_for_status()
14result = r.json()
15print(result["text"])              # Alo, cho mình hỏi đơn hàng của mình bao giờ giao vậy? ...
16print(result["duration_seconds"], "seconds of audio")

About 136 ₫ a minute (8,132 ₫ an hour of audio), at exchange rates from open.er-api.com, 25 October 2026. Live streaming, limits and error codes are on the speech to text API page, and plans are on pricing.

FAQ

Vietnamese speech to text, answered.

Yes, for short files. The uploader on this page turns Vietnamese audio into text with no account for files up to 2 minutes, 3 files a day. For longer files, sign up free and transcribe files of up to 10 minutes and 10 MB each in the dashboard or through the API; that costs $0.00525 a minute, billed by the second, so a 10-minute recording costs about 5.25 US cents.

There is no app to install. The uploader works in the browser on a phone too: open this page on Android or iPhone, pick a voice note, recording or video from your files, and read the Vietnamese text. For typing by voice as you speak, use your phone keyboard's microphone, as described in the voice-typing steps above.

Yes. It runs in a current browser: Chrome, Edge, Firefox or Safari on a Windows PC or a Mac, and Safari or Chrome on an iPhone or Android phone. Files are decoded on our server, so an iPhone voice memo, a WhatsApp .opus note or a MOV video works the same as on a PC. There is nothing to install.

Long-press the voice note in WhatsApp and share or export it to your files; on Android, received voice notes are also kept as .opus files in WhatsApp's media folder. Upload the .opus or .ogg file here and the Vietnamese text appears. Notes up to 2 minutes need no account.

Upload the audio, then open the English tab above the transcript. Vyas, our language model, translates the Vietnamese transcript when you open the tab, and you can copy it or download it like the transcript. Check names, amounts and dates against the Vietnamese text, because a word misheard in Vietnamese carries into the English.

Vietnamese is already written in Latin letters, and the transcript keeps every tone mark. If you need text without tone marks (không dấu), for an SMS system for example, remove them after downloading.

On the clean recording, word for word in both runs, tone marks included. On the 8 kHz phone-quality copy, the short phrase cho mình hỏi was misheard in both runs while the rest was right. That is one sentence, read by a non-native voice; test recordings of your own speakers.

Without an account, 2 minutes per file and 3 files a day. With a free account, up to 10 minutes and 10 MB per audio file in the dashboard or the API, billed by the second. For anything longer, split the recording into parts of 10 minutes or less and send each one; the API takes the same limit.

Yes. Every run of our sample came back with full tone marks. The mistakes on phone-quality audio were whole misheard words, not missing marks.

Other languages, and the other direction.

Need the reverse? Turn Vietnamese text into speech with Pāṇini TTS, free to try without an account.

See speech to text in every language we have tested.

Turn your Vietnamese audio into text.

Free for files up to 2 minutes without an account. Longer files, with a free account: $0.00525 per minute of audio, billed by the second.

Upload a file Valmiki STT API