Buyers and Sourcing Teams
Record supplier calls with factories in Shenzhen or Yiwu and keep English notes with every price, quantity and date. For regular calls, see the meeting transcriber.
Chinese to English Voice Translator: Mandarin Audio to English Text
Upload a Mandarin recording or video and use EzTranscriber as a Chinese to English voice translator for anything already recorded. You get the Chinese transcript in characters, with speakers and timestamps, and the English translation right next to it. New accounts get free credits to start.
Chinese Characters KeptEnglish Side by SideSpeakers and TimestampsFree Credits to Start
From
To
Upload a recording to translate it
Supported formats: MP3, WAV, M4A, AAC, FLAC, OGG, OPUS, WMA
More Tools
Why You Need More Than a Phrase App to Translate Chinese Speech to English
Mandarin packs meaning into tones and short syllables. Shì can be 是, 事 or 市, and only the sentence tells you which. A supplier call, a lecture or a family voice message moves fast, and phrase apps built for live chat translate a few words at a time and then forget them. EzTranscriber writes the whole recording down in Chinese first, then translates it, so you can translate Chinese speech to English with every sentence in context and the original characters kept for checking.
- Tones and homophones that change the meaning of a word
- Fast business calls with numbers in 万 that are easy to misread
- Hours of replaying a recording to write down a single meeting
- Live voice apps that only handle a sentence at a time
- A transcript in one place and a translation in another
What You Get From a Chinese Audio Translator Built on a Transcript
One upload gives you the Chinese text and the English text, lined up sentence by sentence.
Chinese Audio to Text in Characters
The transcript is written in Chinese characters with punctuation, so you can copy a quote, search a name or send the original to a colleague.
English That Reads Naturally
Whole sentences are translated with their context, so time words, measure words and idioms come out as normal English, not a word list.
Side by Side Check
Each English line sits next to the Chinese line it came from. When a number or a name matters, compare them at a glance or click to hear it.
Speaker Labels
A two person call still reads as a conversation. Rename Speaker 1 and Speaker 2 to Manager Li and Emma once and every export follows.
English Subtitles
Export SRT or VTT with the original timing to put English subtitles on a Chinese vlog, lecture or drama clip.
Private Files
Recordings are processed privately and saved only to your history, where you can delete them at any time.
How to Translate Chinese Audio to English in Three Steps
This page opens with Chinese as the spoken language and English as the target.
- 1
Upload the recording
Drop an MP3, M4A, WAV or other audio file, or a video such as MP4 or MOV. A direct link to a media file also works. You see the length and the credit cost before you start.
- 2
Keep Chinese to English
From is set to Chinese and To is set to English. For a Cantonese recording, pick Cantonese in the From list. Sign in, and new accounts get free credits.
- 3
Read and export
The result opens on the English. Switch to the Chinese transcript or the side by side view, click a line to hear it, then download TXT, DOCX, PDF, SRT or VTT.
Chinese Voice to Text Features for Real Recordings
Built for calls, lectures, interviews and videos, from a two minute voice message to a two hour seminar.
Tones and Homophones, Solved by Context
Mā, má, mǎ and mà are four different words, and many characters share the same sound. A speech model that hears the whole sentence picks the character that fits, which is why a full Chinese transcript beats a word by word guess. The transcript keeps the characters the speaker meant, and the English is translated from that text. If you only need Chinese voice to text, read the Original view and skip the English.
Get the Chinese TranscriptMandarin First, Cantonese With a Quick Test
Mandarin from mainland China, Taiwan, Singapore and Malaysia is the strongest case. Cantonese has its own entry in the language list and is transcribed as Cantonese by our main speech engine, but results vary more by speaker and recording than Mandarin, so test a short clip before a long job if you need to translate Cantonese to English. The transcript is written in Chinese characters as the speech model outputs them, usually Simplified for Mandarin; there is no built in switch between Simplified and Traditional characters.
Try a Short ClipTranslate Chinese Video to English Subtitles
Upload a vlog, a drama clip or a recorded class as MP4 or MOV and export the English translation as SRT or VTT. Each caption keeps the time it was spoken, so Chinese to English video translation lands on the right frame in YouTube, Premiere Pro or CapCut. For caption length controls, use audio to SRT, and for any spoken video try video to text.
Translate Chinese Video to EnglishSpeakers and Timestamps in Both Languages
Speaker labels are found in the Chinese audio and carried to every English line, with the time each sentence was spoken. Search either language for a product name or a price, click the timestamp and hear the speaker say it in Chinese.
Translate a CallChinese Audio to Text and English Example
A supplier call recorded in Mandarin. Switch between the Chinese, the English and the side by side view, and click any line.
supplier-call-shenzhen.m4a
12:05 · 2 speakersChineseEnglish
00:04 / 12:05
Search both languagesTXTDOCXPDFSRTVTT
Notice how 五万件 becomes fifty thousand pieces, how 百分之五 becomes five percent, and how the polite 您 turns into a natural English greeting. Names and places such as 深圳 are written as Shenzhen in the English. This is what you download as a bilingual DOCX or as English subtitles when you translate Chinese audio to English.
What to Know Before You Translate Chinese Speech to English
Six details that make a Chinese recording easier to read in English.
Mandarin Accents
Beijing, Shanghai, Taipei and Singapore Mandarin all sound different. They are recognized as Chinese; strong regional accents may need a quick listen on names.
Cantonese
Hong Kong and Guangzhou Cantonese is not Mandarin. Pick Cantonese in the language list and check a short clip first, because accuracy varies more than for Mandarin.
Simplified and Traditional
The transcript uses the characters the speech model writes, usually Simplified for Mandarin. Use a converter afterwards if you need Traditional characters.
Numbers in 万 and 亿
Chinese counts in ten thousands. 五万 is 50,000 and 一亿 is 100 million, and the English uses the numbers your readers expect.
No Verb Tenses
Chinese shows time with words like 已经 and 明天 instead of tenses. Translating whole sentences gives the English the right past, present or future.
Official Use
This is AI translation, not a certified one. For contracts or legal papers, treat it as a working draft and have a qualified translator sign off.
Chinese Transcription Options Compared
Three ways to turn a Chinese recording into English, and what each gives you.
| Chinese Transcription Options Compared | EzTranscriber | Human transcription service | Live voice translator app |
|---|---|---|---|
| Works from a recording or video | |||
| Transcript in Chinese characters | |||
| English translation | Extra cost | ||
| Speaker labels and timestamps | |||
| Bilingual DOCX and subtitles | Sometimes | ||
| Cantonese | Yes, test a clip first | Usually | Varies |
| Turnaround for one hour | Minutes | Days | Not built for it |
Who Uses a Chinese to English Translator for Audio
Anyone with Chinese recordings and readers who work in English.
Students and Learners
Turn Mandarin lectures and podcasts into English notes, then read the Chinese audio to text next to it to learn new words in context.
Journalists and Researchers
Interview sources in Chinese and quote them in English with the original characters on file for every quote you publish.
Video Creators
Subtitle a Chinese vlog or interview in English, or check what a Chinese review really says before you respond.
Families
Voice messages from grandparents and relatives become English text you can read and keep, with the Chinese saved next to it.
C-pop Fans
Read what a Mandarin interview with your favorite singer says in English. For song lyrics with timing, use the lyrics transcriber.
Why People Choose This Chinese Audio Translator
Our factory calls run an hour. I upload the recording afterwards and have English notes with every quantity and date before the end of the day.
Emma Clarke
Sourcing Manager
I research rural migration in China. Having the Chinese line and the English line side by side makes checking my quotes quick and honest.
Daniel Park
Sociology Researcher
My grandmother sends long voice messages in Mandarin. Now my kids read them in English and actually reply to her.
Grace Lin
Nurse
We subtitle Chinese cooking vlogs in English. The SRT timing lines up with the speech, so I only fix dish names.
Kevin Zhou
Video Editor
Chinese Audio Translator FAQs
Quick answers about Chinese transcription and translation with EzTranscriber.
Is this a live voice translator?
No. It is a Chinese to English voice translator for recordings. Record the call, voice message or lecture first, then upload it. You can voice translate Chinese to English from any file and get a full transcript, not just a few spoken words.
How do I translate Chinese audio to English?
Sign in, upload the recording or video, keep From on Chinese and To on English, and start. To translate audio Chinese to English from a video, upload the MP4 the same way. The English opens next to the Chinese transcript a few minutes later.
Can I transcribe Chinese audio to text without translating?
Yes. Every job includes the Chinese transcript first. Read the Original view for plain Chinese voice to text, or turn translation off in the card.
Does it work for Cantonese?
Yes, with a caveat. Cantonese has its own entry in the spoken language list, separate from Chinese for Mandarin. Results vary more than for Mandarin, so test a short clip before you translate Cantonese to English at length. As a Cantonese to English translator for recordings it can work well on clear speech; just do not treat it as a live Cantonese to English voice translator, or as a match for Cantonese transcription services when every word must be exact.
Will the transcript be in Simplified or Traditional characters?
The transcript uses the characters the speech model writes, which is usually Simplified for Mandarin. There is no built in switch between the two scripts, so use a converter afterwards if you need Traditional characters.
How accurate is the Chinese transcript?
Clear Mandarin recordings come out very close to what was said. Noise, crosstalk and strong accents lower accuracy, so check names, numbers and prices in the side by side view.
Can I translate a Chinese video to English subtitles?
Yes. Upload the MP4, MOV or WEBM file, then export SRT or VTT to translate Chinese video to English captions. A public YouTube link works too: paste it into the YouTube tab above. Bilibili or Douyin pages may not load, so download the video and upload it, or paste a direct link to the video file.
Can I export the Chinese and the English together?
Yes. In the side by side view every export is bilingual: TXT, DOCX, PDF, SRT and VTT carry the English with the Chinese line under it.
Is it better than a regular translator from Chinese to English?
For audio, yes. A text translator from Chinese to English needs typed text first. Here you translate Chinese voice to English straight from the file, and translate voice Chinese to English with speakers and timestamps kept, so it works as a Chinese to English translator voice tool for recordings.
Does it make an English voice over?
No. You get text: the Chinese transcript, the English translation and subtitle files. It is not a Cantonese translator audio dubbing tool or a voice over generator, and it does not speak the English aloud.
How much does it cost?
New accounts get free credits for a first recording. After that, transcription uses credits per minute and translation adds one credit per started 10 minutes, whether you translate Chinese to English audio or another pair. Plans are on the pricing page.
Is my recording private?
Yes. Files are processed privately, never shared or published, and saved only to your own history, where you can delete them at any time.
Translate Audio From Other Languages
The same tool, set up for other language pairs.
Ready to Turn Chinese Recordings Into English?
Upload a Chinese recording and get the transcript in characters and the English translation side by side, with speakers and timestamps. Create your account, try the Chinese to English voice translator with free credits and keep both versions on file. For other pairs see the audio translator, or start from the main audio to text converter.