get started with Chinese video transcription and translation

you're a film maker, editor or a producer looking to have Chinese video footage transcribed/translated to English. Your crew shot tons of Chinese footage in Mainland China, Taiwan, Hong Kong or another country with a large Mandarin Chinese or Cantonese speaking population such as the United States or Singapore and your editor doesn't speak a word of Chinese. Good news. We're here to help!


Chinese Video Transcription Questions

We've got questions—You've got answers. Before we quote a job, we like to learn about your project. Here are common questions we'll ask you:


1. Does the video feature raw footage or a final program? How will you use the transcript ?

A common scenerio is a video with raw footage where the purpose of the transcript is to create a script. Or the raw footage could be intended so a video editor who does not speak Chinese can still edit the foreign language footage.

if it's a final program, perhaps you are looking to use the transcript to create captions or subtitles or a voice-over script to dub in another language. The process, budget and deliverables vary depending on what your final deliverable will be. Let us know what type of program it is, for example a corporate video, a feature film, an episode of a series. Luckily we've got many years of experience doing all of the above and can guide you through each step of the process.


2. Are you looking to transcribe and or translate a one-on-one interview, a multi-person interview, a presentation, b-roll or other type of Chinese footage?

we format transcripts differently based on the type of footage. If it's a one-on-one interview, you may prefer to have only the interview subject's answers it not have a need for us to include the questions. If the questions are not mic’d transcribing them may take some deciphering and thus extra time and there may be inaudibles.


3. Would you like speaker IDs included in the transcript?

there may or may not be a need to identify the speakers. If it's a one-on-one interview in Chinese and you only need the answers transcribed, since there's only one interview subject, adding a speaker identification for each time the interviewee answers may be unnecessary.


4. What else should be included or skipped in the transcript?

interview footage frequently has post comments, extraneous chatter and an interpreter who translates the questions and answers. Do you need any of this included in the transcript?

While we can’t list all the variations of transcripts that exist, we have compiled examples of formats optimized for one-on-one interviews, group interviews & discussions and more:

Production Transcript Examples

5. How frequently should we insert a timecode or timestamp?

in an interview setting, typically we insert a timecode at the beginning of every answer and approximately every 30 seconds thereafter. If you also want the questions transcribed we can insert an optional timecode at the beginning of each question as well. Thus if your interviewee gives a 60 second response to a question, there would be a time code mark at the beginning of the answer and approximately 30 seconds later. If your footage is unstructured – for example, Reality TV dailies, then we just insert a timecode mark every 30 seconds if there is no obvious place to mark the beginning and end of an audio response. (e.g. a lot of people chatting amongst themselves.)

the timecodes for production transcripts are accurate within 1-3 seconds. Frame accurate timecodes are applied whenever specified by the client, for spotting lists, continuity scripts, CCSLs etc.

6. Should the transcript be verbatim or other?

unless agreed otherwise, the transcripts are verbatim, i.e. word for word including ah's, hmms, false starts and stutters, repetitions, distracting speech patterns.


7. From which country and region does the spoken Chinese originate?

we offer transcription services in Chinese languages and dialects including Mandarin and Cantonese. We also transcribe Chinese spoken by native speakers or speakers of Mandarin or Cantonese as a second language speakers who reside in other parts of the world.


8. What is your deadline to receive the transcripts?

our standard turn-around time is 4-5 business days. We also offer rush service. Additional time may apply for volume work.

we will discuss with you an agreeable delivery schedule based on your needs, quantity of footage and budget. We can deliver on a rolling basis.


9. What format are the video receivables?

We accept all major audio/video formats including CD, DVD, tape, and most digital video and sound files including mp4, mov, wav, MP3, aif, aiff and Real Audio etc. We also offer digital encoding and transcoding services from tape.

If you need a timecoded transcript, we suggest the following receivables work file format.

  • codec: H264/MP4
  • size: 320x180 (16:9) or 320x240 (4:3)
  • video bitrate: approx 250 kpbs
  • audio format: 48 kbps 44 KHz stereo CBR
  • TC: Window Burn (upper) - please advise frame rate. Most of our projects are 23.98 fps.
  • filenaming Convention: “yourcompanyname_projectname_language_TRT” (example: Corp_ProjectA_Mandarin_15min(.mov).
  • files may be uploaded to our FTP. We will supply you with a custom ftp account.
  • TRT: To enable faster processing of foreign language footage, please break up files into approx. 30 min each.
  • timecode jumps: 3 seconds of black between jumps is helpful to our translators.

For a cost estimate, please provide us the details of your project, by calling us at 212-489-6035 or email info@iprobesolutions.com.