Video Transcript Generator

Generate a video transcript in seconds with industry-leading AI transcription that includes speaker labels, time codes, and even chapters. Descript’s free video transcript generator is perfect for marketing videos, podcasts, YouTube videos, subtitles, and more.

How to transcribe a video in seconds—with time codes & speaker labels

Step 1

Upload a video to generate a transcript

Create a new project in Descript and upload the video files you want to transcribe by dragging and dropping them into the editor. You’ll be prompted to choose a transcription language. If there are multiple voices, you’ll be asked to identify the number of speakers, as well as their names and voices so Descript can automatically label them for you within the video transcript.

Step 2

Edit and customize your transcript

By default, deleting or editing the text in your transcript will edit your video too. So you’ll want to enter Correct mode by pressing ‘C’ or highlighting and right-clicking on the text you want to correct. This lets you correct the text or all instances of a transcription error while keeping the text and audio in sync. Alternatively, you can use Write mode (CMD+E or CTRL+E) to freely edit the transcript as you would a doc.

Step 3

Export your transcript

When you’re happy with your transcript, export it by going to Publish > Export > Transcript. Choose your preferred format: Microsoft Word (.docx), HTML (.html), Markdown (.md), Plain text (.txt), or Rich Text Format (.rtf). Then customize the settings for speaker labels, timecodes, and chapter markers. Finally, click export to download the transcription file or copy the transcript to your clipboard.

Download the app for free

Create a podcast, a video, and all your social assets using Descript. It’s as easy as editing a doc.
Sign up for this tool
Try Descript for free →
HomeTools
Video Transcript Generator

Video Transcript Generator

Generate a video transcript in seconds with industry-leading AI transcription that includes speaker labels, time codes, and even chapters. Descript’s free video transcript generator is perfect for marketing videos, podcasts, YouTube videos, subtitles, and more.

Get started →
How to transcribe a video in seconds—with time codes & speaker labels
  • 3
    Create a new project
    Drag your file into the box above, or click Select file and import it from your computer or wherever it lives.
Step 1
Upload a video to generate a transcript

Create a new project in Descript and upload the video files you want to transcribe by dragging and dropping them into the editor. You’ll be prompted to choose a transcription language. If there are multiple voices, you’ll be asked to identify the number of speakers, as well as their names and voices so Descript can automatically label them for you within the video transcript.

Step 2
Edit and customize your transcript

By default, deleting or editing the text in your transcript will edit your video too. So you’ll want to enter Correct mode by pressing ‘C’ or highlighting and right-clicking on the text you want to correct. This lets you correct the text or all instances of a transcription error while keeping the text and audio in sync. Alternatively, you can use Write mode (CMD+E or CTRL+E) to freely edit the transcript as you would a doc.

Step 3
Export your transcript

When you’re happy with your transcript, export it by going to Publish > Export > Transcript. Choose your preferred format: Microsoft Word (.docx), HTML (.html), Markdown (.md), Plain text (.txt), or Rich Text Format (.rtf). Then customize the settings for speaker labels, timecodes, and chapter markers. Finally, click export to download the transcription file or copy the transcript to your clipboard.

Generate a video transcript—and more—in seconds
Up to 95% accurate transcription in 22+ languages

Get industry-leading AI transcription in multiple languages, including English, French, Dutch, Italian, and more. Get better results over time as you add uncommon or difficult words to the transcription glossary so they get transcribed correctly every time.

Automatically label speakers & remove filler words

Save a boatload of time on manual transcription editing. Speaker Detective detects and adds speaker labels to your transcript so you don’t have to. Plus, potential transcription errors and filler words like “uh” or “you know” are automatically flagged so you can remove or fix them in one click.  

A unique transcript editor with built-in AI

Unlike other transcript generators, Descript is packed with AI features that unlock new workflows made for video creators. Built-in AI Actions help you do more with your transcript, like add chapter titles, or generate a YouTube video description, summary, or blog post.

Questions? We have answers
How can I turn a video into a transcript?

You can convert video into a transcript by manually transcribing it, or by using an automatic transcription tool such as Descript. Just drag and drop your video into a new project in Descript to generate a transcript in seconds, including speaker labels and time codes.

Can I transcribe my video for free with Descript?

Yes, you can transcribe video to text with Descript for free. With the free plan, you get 1 hour of transcription per month and can download the transcribed text in multiple formats. Paid plans starts at $12 per month to unlock 10 hours or more.

Can AI write my script for me with Descript?

Certainly! Just click on the Ask AI button and you can ask it to write a script, generate an outline, or brainstorm ideas with you. Once you’ve entered your instructions in the chat prompt, Ask AI will generate a script. You can then add it to your project or ask it to refine its answer.

How do I remove filler words in my transcript with Descript?

In the Actions panel on the top-left, click on Remove filler words. The dropdown list will display all the filler words that can be removed, such as “mmm, “um,” “uh,” and “umm.”

What languages can I transcribe with Descript?

Descript supports transcription in over 22 languages, including English, German, French, Italian, Spanish, Portuguese, Romanian, Malay, Turkish, Polish, Dutch, Hungarian, Czech, Swedish, Croatian, Finnish, Danish, Norwegian, Slovak, Catalan, Lithuanian, Slovenian, and Latvian.

This is some text inside of a div block.
Descript is the only tool you need to write, record, transcribe, edit, collaborate, and share your videos and podcasts.
What is the point of this tool?
Descript is the only tool you need to write, record, transcribe, edit, collaborate, and share your videos and podcasts.
More than a video transcript generator
With an automatic video-to-text converter, AI support, and collaboration features, Descript isn’t your average video transcription software.
  • Video editing
    Edit videos and generate accurate transcripts in one editor to produce all your social media content, educational videos, or podcasts.
  • Text-to-speech
    In the same editor that generates your transcript, you can write a script and generate realistic AI speech from a stock voice or your own voice clone.
  • Publishing
    Share your videos with a Descript web link that includes a fully-featured video player with a searchable transcript.
  • Captions & subtitles
    Turn your video transcript into subtitles and captions that remain synced even as you cut or edit.