checking the microphone and webcam

Automatically Transcribe YouTube Video/Audio with Google Docs

Part 1: How to Transcribe YouTube Video Automatically for Free [2 Ways]

Besides the basic video editing features on the YouTube platform, you can now quickly transcribe YouTube videos to the text as well. The good thing is, you can either use the automatic transcription feature that YouTube offers, or upload it manually while adjusting the timing as you go further.

Below are the two methods to transcribe your YouTube videos for free:

Method 1: Use the Automated Transcription Service on YouTube

As the name suggests, YouTube automatic transcription service works automatically. This means you don’t even have to click the ‘Transcribe’ button anymore to transcribe a YouTube video, and the website takes care of it on its own. All you need to do is, choose English as the language of the video when setting up subtitles. You can follow the instructions given below to do so:

Step 1 Upload a Video

Sign in to your YouTube account, click your profile picture from the top-right corner, and click YouTube Studio from the menu. Next, click CREATE from the upper-right corner, click Upload videos from the menu, and drag and drop a video from your computer to the Upload videos box that appears next.

Step 2   Select Transcription Language

Step 2 Select Transcription Language

On the Details page of the next box that appears, scroll down and click MORE OPTIONS, and select English in the Video language drop-down list under the Language, subtitles, and closed captions (CC) section.

Step 3   Publish the Video

Step 3 Publish the Video

Follow the on-screen instructions from this point to publish the video, and wait while YouTube automatically transcribes and adds the close captions to it.

Note: Depending on the duration of the clip, the time YouTube would take to transcribe may vary.

After YouTube has transcribed the video, you can download the transcription file in your preferred format. The instructions are given below explain how you can do so:

  1. Get to the Subtitles Window

While on the YouTube Studio page, click Subtitles from the left pane to go to the Channel subtitles page. And then click the video you want to modify.

  1. Get to Classic Studio

In the video subtitle page of the target video, hover mouse on the Published Automatic status under the Subtitles column, click the Options icon (with three vertical dots) that appears, and click Edit on Classic Studio.

 Download Transcription File

  1. Download Transcription File

Click and open the Actions drop-down list from the top-left corner of the left pane, click your preferred transcription format including .vtt, .srt and .sbv from the list, and save the file on your local hard disk.

Method 2: Get YouTube Transcription when Watching

Method 2: Get YouTube Transcription when Watching

In addition, if you are watching any other video, you can make YouTube transcribe that for you as well. You can follow the instructions given below to get the YouTube video to text transcription:

Step 1: Play the Video

Go to the video on YouTube and start playing it. Make sure NOT to get to full-screen mode as doing so would hide the option to transcribe the clip.

Step 2: Enable Transcription

Click the More icon (with three horizontal dots) from under the bottom-right corner of the video player, and click Open transcript to see the video transcription in the Transcript pane that appears in the right.

Step 3: Manage Timestamps

Click the Options icon (with three vertical dots) from the top-right corner of the Transcript pane, and click Toggle timestamp to enable or disable the timestamps in the video transcription.

Limitations of Using YouTube Transcribe

Although YouTube’s automatic transcription is a decent feature that saves you a lot of time, since Google uses machine learning algorithms to convert the speech to text, the level of accuracy may vary depending on the accent of the speaker, and the clarity of the audio the video has. Also, even sometime you may not be satisfied with the end-results.


About Us

Hi, I’m Tosh Lubek. When I’m not working on this website I run an audio & video production business producing website videos and broadcast advertising for local and national clients. I also teach business owners and entrepreneurs how to create their own videos.


For our setup, we need to know a few things:

  1. What options to pass to youtube_dl
  2. The AssemblyAI endpoints
  3. Some other constants

For youtube_dl options, we want to download the video and extract the audio, so we’ll go with bestaudio as our format option. Then because we need to get the audio, we need to pass a postprocessor, and that’s where ffmpeg comes in. You’ll notice I also added an ffmpeg location of ‘./’ and that’s for Windows users who have moved the ff- binaries up to the folder with your program in it. I also added an outtmpl (output template) and set the name of the file to be equal to the YouTube id of the video, this is totally optional, I did it because I find that the title of the file can get long and cumbersome to work with in some settings, especially if there are spaces in it.

We’ll interact with two of the AssemblyAI endpoints here, one to upload the audio of the YouTube video to, and the other to get a transcription from. We’ll define them in our code like so:

Finally, we’ll set up a couple more constants, the headers that we need to send when interacting with the AssemblyAI API, and the desired chunk size when reading a file. Which we will set up like so:

We’ve installed our prerequisite libraries and we set up our constants, now it’s time to dive into making the app itself.

Let’s break this down into four steps (and conveniently also four commands):

  1. Downloading the audio from YouTube (download)
  2. Uploading the audio file to Assembly (upload)
  3. Transcribing the audio file via Assembly (transcribe)
  4. Getting the transcribed text file (poll)

How to Transcribe a Youtube Video to Text with a Transcription Service 

Using a transcription service for transcribing a YouTube video to text is the easiest option. Here’s how to get started.

1. Upload Your YouTube URL to a Trusted Transcription Service

Rev is the most accurate transcription solution available for your money, and offers both professional transcription services and automatic transcription services. Upload your YouTube URL here to get started by clicking “Paste a URL”

Get a YouTube Video Transcript

Get a YouTube Video Transcript

2. Select your Optional Add-on Options

You can choose to rush your order, add timestamps, get an instant draft transcript, and more. These options are all additional fees, but they are completely optional.

3. Click “Checkout” and Receive your T

3. Click “Checkout” and Receive your Transcript

The length of time for our professionals to transcribe your video depends on the video length, but most videos just take a few hours. Our automatic transcription service is nearly instant, but will be less accurate.

You will receive your YouTube transcript in an email or in your account when it is finished!

Methods used to transcribe audio from video to text

Recently I recorded interviews with 36 teachers. Although they were all English speakers, they were Scottish and represent more of a challenge for the speech recognition software.

Since I knew one of the apps would only load files that were under 60sec I chose an interview clip that was 55.5 seconds as my test file. The audio file format was 48kHz, 16 bit, stereo .wav file.

Even though I don’t enjoy hand transcribing videos, I did that to make sure the transcription was correct. It turned out to be 165 words, so, a word rate of almost 3 words per minute.

Although I tested seven different options, each audio to text converter involved one of two ways of getting the data, that’s the recorded speech, into the speech to text program.

The first involved playing the audio recording into a microphone connected to a computer, or in one case, my iPhone.

While the second involved uploading the audio file to an online platform or cloud service.


If you need a quick transcription of an audio memo, this is an easy way to do it. The results are not always perfect, but it can be helpful.

We have a lot more YouTube Hacks, Tips and Resources here.