You just recorded a podcast and now the real work begins: cutting out all the uh’s, removing long silences, and re-recording that one sentence you stumbled over. Or does it? Descript flips the process by letting you edit your audio and video as if you’re editing a Word document. Delete a word from the text and it disappears from your recording.
Who is behind Descript?
Descript was founded in 2017 by Andrew Mason in San Francisco. You might know Mason from Groupon, the coupon platform he previously founded. After Groupon, he started Detour, a company that created audio tours for cities. For those tours, his team had a problem: editing audio took way too much time.
Mason therefore built an internal tool that allowed his team to edit audio by simply modifying the transcribed text. That tool worked so well that he decided to turn it into a separate company. That’s how Descript was born. The company grew rapidly and raised more than $1 million from investors like the OpenAI Startup Fund, Andreessen Horowitz, and Redpoint Ventures.
Today, Descript has more than 6 million users. The tool is used by major media companies like The New York Times and VICE. In 2023, Descript acquired the podcast recording platform SquadCast, further strengthening their position in the podcast market. The company continues to grow and regularly adds new AI features.
Who is Descript for?
Descript is primarily aimed at people who regularly create audio and video without a professional editing background. Think of podcasters who want to clean up their episodes, video creators making YouTube content, content marketers producing educational videos, and freelancers who need to quickly edit interviews.
The tool is less suitable if you’re just looking for a simple audio cutting tool. In that case, there are cheaper and simpler options. It’s also not the right choice for Hollywood-style film productions with advanced color grading and visual effects. For that, you need software like Adobe Premiere Pro or DaVinci Resolve.
What can Descript do?
The free version of Descript already offers a lot of functionality, such as basic transcription and text-based editing. For advanced AI features like Overdub, Studio Sound, and unlimited transcription, you need a paid plan. Here are the main capabilities:
- Text-based video and audio editing: This is the core feature. Descript automatically transcribes your recording and links each word to the exact moment in your audio or video. Want to remove a sentence? Delete the text. Want to flip two sentences? Cut and paste in the text. No more cutting in timelines.
- Overdub (AI voice cloning): With this feature, you create an AI clone of your own voice. Mispronounced a word? Type the correct text and Overdub generates it with your voice. No need to re-record. This works best for small corrections, not entire new sentences.
- Studio Sound (AI audio enhancement): This feature removes background noise, echoes, and static from your recording. It turns a recording in a noisy room into studio-quality sound. Users often cite this as one of Descript’s strongest features.
- Automatic transcription in 22+ languages: Descript automatically transcribes your audio in more than 22 languages. The accuracy is high, especially in English. You can manually adjust the transcription afterwards if there are any errors.
- Automatic filler word removal: With one click, Descript removes all uhs, ums, and ahs from your recording. This saves an enormous amount of time when editing interviews and podcasts where people use a lot of filler words.
- Screen recording functionality: You can record your screen, including your webcam and microphone. Useful for tutorials, product demos, and presentations. After recording, you edit everything through the text interface.
- Multitrack audio editing: You can edit multiple audio tracks simultaneously, for example with a podcast featuring multiple speakers. Each speaker gets their own track and you can adjust them individually for volume and effects.
- Green Screen (AI background removal): Without a physical green screen, Descript removes your background and replaces it with another image or video. The AI detection works reasonably well, but not perfectly with complex hair edges or moving objects.
What does Descript cost?
Descript has a free plan to get you started. With this, you get up to 1 hour of transcription per month and can export videos in 720p with a watermark. AI credits are limited, so you can only use features like Overdub and Studio Sound to a limited extent.
The Hobbyist plan costs $1 per month, or $1 per month when billed annually ($1 per year). This gives you 10 hours of transcription per month and lets you export in 1080p without a watermark. The Creator plan costs $1 per month, or $1 per month when billed annually ($1 per year). This plan offers 30 hours of transcription and more AI credits.
For teams, there’s the Business plan for $1 per month, or $1 per month when billed annually ($1 per year). This plan has unlimited transcription and additional collaboration features. All paid plans can be tried free for 7 days before you pay.
What should you watch out for?
Descript has some drawbacks that users regularly complain about. The software can become slow with large video files or long projects. Rendering and exporting sometimes takes a long time, especially with videos over an hour. This can be frustrating when you want to finish a project quickly.
The interface isn’t always intuitive. New users often find it difficult to understand where certain features are located and how the workflow works. There’s a learning curve, especially if you’re used to traditional video editors like Adobe Premiere or Final Cut Pro.
Because Descript is cloud-based, you need a stable internet connection. Without internet, you can’t work. This is a problem when you’re on the go or in locations with poor wifi. Also, uploading large files to the cloud takes time.
The Overdub feature sometimes has lip-sync issues. The generated audio doesn’t always perfectly match the movements of your mouth in the video. This is especially noticeable in close-ups. For small corrections it works fine, but for longer sentences it becomes less natural.
Finally, Descript isn’t suitable for complex video editing. You can’t do advanced color grading, add complex visual effects, or create professional motion graphics. It’s a tool for quick content production, not for cinematic productions.
Descript alternatives
There are several alternatives to Descript, each with their own strengths:
- Riverside.fm: Choose this if you primarily record remote interviews and podcasts. Riverside focuses on recording high-quality audio and video, even with poor internet connections. However, the post-production editing is less advanced than with Descript.
- Adobe Premiere Pro: Choose this if you’re creating complex, professional video productions with advanced effects. Premiere Pro is much more powerful but also much more complex. You’ll miss Descript’s simple text-based workflow and the learning curve is much steeper.
- Cleanvoice AI: Choose this if you only want to clean up audio and don’t need a video editor. Cleanvoice focuses purely on removing filler words and background noise from podcasts. It’s cheaper than Descript but lacks all video functionality.
Frequently asked questions
Here are answers to the most frequently asked questions about Descript:
What is Descript?
Descript is an all-in-one AI tool for editing audio and video. You edit your media by simply adjusting the generated text (transcription). If you delete a word from the text, it also disappears from your recording.
Can I use Descript for free?
Yes, there’s a free plan available. This gives you 1 hour of transcription per month and lets you export videos in 720p with a watermark. For more hours and advanced features, you need a paid subscription.
What is the Overdub feature?
With Overdub, you can create an AI clone of your own voice. This allows you to fix mistakes in your audio by simply typing the correct text, without having to re-record. This works best for small corrections of a few words.
Conclusion
Descript is a strong choice for podcasters, video creators, and content marketers who regularly edit audio and video without professional editing experience. The text-based workflow saves a lot of time, especially when removing filler words and making rough cuts. Studio Sound and automatic transcription are valuable features that enhance production quality.
The tool does have drawbacks. With large projects, the software can become slow and the interface isn’t always intuitive. It’s also dependent on an internet connection and less suitable for complex video productions. If you primarily record remote interviews, Riverside.fm is a better alternative. For professional film productions, Adobe Premiere Pro is a better choice.
For those who regularly make podcasts or YouTube videos and want to edit quickly without technical knowledge, Descript is worth trying. Start with the free plan or use the 7-day trial of a paid subscription.
