Whether you’re using that conversation in an article or a research project or editing it into a video or podcast, it’s time to transcribe it.
Where do you start? You start by typing “how to transcribe an interview” into Google, but you probably already did, and that’s what brought you here. Hi!
Anyway, you’re in the right place, because Descript will automatically transcribe your interview (and let you edit the audio or video right from the transcript). But if you want to learn more about different transcription options, here’s what you need to know.
An interview transcript is an audio track converted into text so people can read it. Before you start transcribing, it’s worth considering the transcript’s ultimate purpose.
Praise the robots, for they allow us to save time.
Not only is a lot of transcription software free (or free to a point), but it also takes the drudgery out of the transcription process. Some errors and typos are inevitable, so you’ll want to edit the text afterward, even if you use a high-quality transcriber like Descript.
Descript automatically transcribes any file you import; just drag your audio into the app, wait a few seconds, and you’ll have a complete transcript.
That, in our very biased opinion, makes Descript the best transcription service, hands down. But here are some other transcription tools:
Open your Descript app, then click New project in the upper right corner.
On the following screen, name your project and click Choose a file to transcribe.
Choose your file.
After selecting open, Descript will automatically transcribe your audio or video file.
Next, Descript will ask you to identify the speakers in your file. If it’s just you and another interviewee, select two from the dropdown menu.
Descript will then ask you to identify each speaker. We'll play you a short clip from your file, and you'll type in the speaker's name.
Then click Add “Name” as speaker. Easy peasy!
Now you’ve got a transcript ready for editing.
You probably see some mistakes already. With Descript, you can edit your audio by editing the text in the transcript.
If you don’t like a word or sentence in your transcript, highlight it and press delete on your keyboard. You can also correct words and punctuation quickly with a few handy keyboard shortcuts.
You can also choose to automatically correct any mistakes the AI made. Access them in the upper right hand corner of your transcript.
You’ll find shortcuts like:
At this point, you’ve got a clean transcript ready to go. The last step here is to export the transcript and give it a good proofread.
First, click the Publish button in the top right corner of your screen. Click the Export tab and then the Transcript button.
Before exporting the file, you can choose to include:
You can also choose how often you want the timestamps to appear in your transcript file, and the format of the transcript file. Once you hit Export, you can find the file on your computer.
Here’s an example of what we just made.
💡PRO TIP: If you’re publishing the transcript as-is, hire an editor or use Grammarly to tighten it up. There will likely be grammar errors you missed during editing. It’s normal. Edit the transcript before pushing it live to truly make it shine out in the wild.
The above process for transcribing interviews is super easy, but if you’re up for a bit more of a challenge, or have more budget, there are two other types of transcription methods.
Transcribing interviews manually is the “roll up your sleeves and type like the wind” approach. There aren’t many fancy tools here, just you, your audio recording, some headphones, and a word processor. (There are tools that will let you slow down and go back in a recording without leaving the keyboard, though — our managing editor has trusted the manual transcription tool from Wreally for years.)
The upsides are that it’s free (assuming you have the basic interview recording equipment), and you’ll get very familiar with the material. The downsides are that it is time-consuming, and if you don’t have fast typing speed, it could feel like a Sisyphean task.
Here’s a rundown of how to get started.
Nothing beats that human touch — for now at least. (The robots will replace all of us in the end.) Sending your audio files to a service that will farm it out to an actual person for transcription has obvious benefits.
Namely, people understand the nuances of human speech better than a computer will, and if you hire a quality service, you won’t have to worry too much about editing what they send back.
On the other hand, a transcript made by a human will cost you more than one made by software, and the level of detail means it’ll also take a lot of time.
Here are a handful of respected agencies to try:
Here’s an example of an edited transcription with timestamp headers:
Interviewer (Content Marketer, Susan): Good afternoon, Mike. Thank you for taking the time to be with us today.
Mike (Founder, MarketingTool.io): Hi Susan, thank you for having me.
Susan: Mike, can you briefly tell us what inspired you to create MarketingTool.io?
Mike: Absolutely. I saw a gap in the market for user-friendly and cost-effective marketing tools. I wanted to create something that every business could use.
Susan: Interesting. What's the core functionality that sets MarketingTool.io apart from other tools?
Mike: Our AI-driven analytics. It not only provides accurate data but also insightful suggestions on how to improve your marketing strategies.
Susan: That sounds like a game-changer. Can you tell us about a significant challenge you faced while developing this tool?
Mike: Building the AI was the toughest part. It had to be smart yet straightforward. The balance was challenging but we managed it.
Susan: I can imagine that was a significant task. Moving forward, what new features can your users expect from MarketingTool.io?
Mike: We're planning to integrate more social media platforms and add real-time tracking capabilities.
The nice (and maddening) thing about transcribing is that you know you can always get a free transcription by just doing it yourself.
But if you have the option of hiring a transcriptionist to do it, it’s definitely something to consider. Transcribing an interview podcast is fun once or twice, but if you have a whole bunch of long, say, qualitative research interviews to get into text, you’ll be kicking yourself and/or going insane before long.
The easiest way to transcribe an interview is by using an automated transcription service like Descript. These apps use AI to convert spoken words into text, reducing the manual effort and time required to transcribe an interview.
To transcribe an interview, you would simply upload the audio or video file to a software like Descript. It’ll generate a written transcript in minutes and you can edit for accuracy.
If you’re using an audio-to-text app, the turnaround time to transcribe a 60 minute interview is minutes. You’ll need to spend some time reviewing and correcting errors. If you’re transcribing the interview manually, it could take you up to six hours considering you have to pause, rewind, and review way more often.
Brandon CoppleHead of Content at Descript. Former Editor at Groupon, Chicago Sun-Times, and a bunch of other places. Dad. Book reader. Friend to many Matts.