Add automated subtitles and captions to your videos using Descript’s AI-driven Subtitle Generator. This tool works for audio to caption or video editing, and you can try it free with up to one hour of audio to subtitle each month.
Get started
These companies use Descript. Not bad!
01
Upload a video to transcribe
Open a new project, then pick any MP3, MP4, WAV, MOV, or similar file for transcription. Our Subtitle Generator turns your content into a transcript, letting you tag each speaker so their names appear correctly in the final captions.
02
Edit your video transcript
Descript flags filler words like “um” or “like.” Remove them entirely or retain what feels natural. Use Correct mode (press C) to tweak your subtitle text, staying synced with each speaker. This keeps your audio to caption process simple and accurate.
03
Generate your subtitles
For soft subtitles, go to Publish > Export > Subtitles and pick SRT or VTT. You can add or hide speaker names and set character or line limits. Then download it for your platform. For hard subtitles and embedded captioning, take advantage of the Text tool to style and bake your subtitles into an export. You can even generate subtitles from audio free as part of your monthly allowance.
Always auto-synced captions
Your audio and subtitles stay perfectly in sync, even if you cut or move the transcript, MP3, or MP4 timeline. Our text-based editing makes finalizing captions or full subtitles painless.
Fast, accurate subtitles in 22+ languages
Turn an hour of audio to subtitle instantly. Descript’s AI reaches about 95% accuracy in English, French, Spanish, and many others — so you can create subtitles from audio without stress.
Subtitles for access and engagement
Subtitles bolster accessibility and engagement for diverse audiences. You can also burn in styled captions if you want them permanently on screen, or provide closed caption options for flexible viewing.
Descript is an AI-powered workspace for audio and video, offering text-based editing for podcasts, blogs, and beyond.
Remove filler words
AI transcription identifies filler words so you can cut those distracting “uhs” and “ums.”
Captions
Add animated text that follows each speaker line by line or even word by word.
Publishing
Share on YouTube, Wistia, or other platforms with subtitles embedded or exported separately.
Templates
Experiment with pre-made subtitle designs to keep your workflow efficient.
30 minutes / month of dubbing in 20+ languages
Is Descript’s Subtitle Generator free?
Yes! You get one free hour of transcription monthly to create subtitles from audio or video.
Can I auto-generate subtitles for YouTube videos with Descript?
Absolutely. Transcribe your video, refine the text, then export an SRT or publish directly to YouTube — all in one workflow.
What are captions in Descript?
Captions embed auto-generated subtitles in any font, size, or style, built from your transcript. You can caption a full video or just sections in a few clicks.
What’s the difference between soft subtitles, hard subtitles, and closed captions?
Soft subtitles are optional and separate from the video. Hard subtitles are baked into the video and can’t be turned off, often seen on social media. Closed captions include sound effect descriptions or ambient noise notes. Descript helps with all three, so you reach more viewers and keep them engaged.
What subtitle file formats can you export with Descript?
You can export SRT or VTT for other apps, or produce captioned MP4 files for immediate sharing.
