There are tons of AI programs online that automatically generates a transcript from an audio or video file, but many of them charge a per minute or a monthly or annual rate to use them. Otter.ai is the best one I’ve used in terms of accuracy of the final transcript and for allowing one to use their basic services free of charge for a month and without requiring your card details in advance. You can also use YouTube to auto transcribe your audio or video file.
Using YouTube to create an auto transcript is not easy by any means. But if you don’t have the dollars to pay for a transcription service or bot, then it’s worth putting in the effort to learn how to use YouTube to output a transcript. Just to be clear, there are not many bots who can accurately transcribe human speech yet. So you will still need to edit the transcript. You’ll just skip the typing part of transcription. To start off with, if you have a video file, then skip to stage 2.
Stage 1: You need your audio file in an MP3 format. If it’s an audio file without any video, you need to convert it into an MP3 format. YouTube won’t accept an audio file, so we need to convert the audio file into a video file that YouTube will accept. I use Tovid.io to convert my audio into a YouTube-ready video file. You can also add a JPEG image. Once you’ve converted and downloaded your file you can move to the next stage.
Stage 2: Log into your YouTube account. To upload a video on YouTube, you need to have a YouTube account. Once you’ve logged in, click on the circle with your profile image in the top right-hand corner. Click on YouTube Studio. On the Dashboard, Upload Videos. In Details, click Not made for Kids, click Next. Click Next on Video Elements. Click Private under Visibility. Click Save. Depending on the length of your video, it could take a couple of hours for your transcript to be read. I usually upload my videos at night and find the transcript ready by the following morning.
Stage 3: To check if your transcript is ready, click on Videos in the left-side menu. Click on the Video under Channel Video. You’ll be taken to the site on YouTube where the video is being hosted. Click on the three dots next to Save. If the transcript is completely transcribed, it will be there. If not, return in a few hours. Click on Open Transcript. An auto transcript will appear on the right-hand side. Now, click on the vertical three dots next to Transcript. Click on Toggle timestamps to turn the timestamps off. Highlight the transcript and right-click or Ctrl+C to copy the transcript.
Stage 4: Paste your copied transcript into Word by either right-clicking or paste with Ctrl-V. The transcript is still not ready for editing. It will be in a raw format without any punctuation. Use the Word Ctrl+H command to replace um, uh, you know, one at a time with blank spaces i, i’m, etc. with the correct spelling throughout the document. You can also replace the line breaks at the end of sentences by typing ^p in the Find dialogue box and replace it with a blank space. Also, remove blank spaces with the CTRL+H command by typing in a blank space with your space bar in the Find dialogue box and remove spaces from the Replace box. I use Ctrl+H to remove duplicate words or anything errors or speech patterns that occur frequently.
I find the YouTube transcript to be nearly as good as Otter.ai, and sometimes better with heavy non-English accents, but of course requires a lot more work.
