Features of the caption generator
Automatic Subtitles From Your Video
HeyGen's AI subtitle generator transcribes your audio to generate subtitles, timing every caption line to the moment it is spoken. The subtitle generator automatically flags names, jargon, and low-confidence words so you can correct them quickly, then export accurate subtitles that read cleanly on any screen.

Animated, word-by-word captions
Start from a caption template, then set the subtitle font, colour, size, and spacing, and pick a look: clean single lines, word-by-word pop, or karaoke highlight. Add animated effects and your brand colours for a personal touch, and align the text clear of the bottom third on vertical clips.

Translate Subtitles into 175+ Languages
One caption track becomes many. The AI video translator converts your subtitles into 175+ languages and can dub the audio with lip-synced voice, so one video reaches global viewers without re-recording, re-timing, or hiring a separate translation vendor for each market.

Burn captions in or export an SRT
Choose how captions are delivered. Burn subtitles into the frames for TikTok, Reels, and Shorts as burned-in text that always shows on silent autoplay, or download a separate SRT, VTT, or TXT file for platforms that let viewers toggle captions on and off.

Create and caption in one place
Most caption tools stop at video editing on footage you already shot. HeyGen is all-in-one: the AI video generator turns a script into a finished clip, then captions it in the same workspace, so writing, recording, and subtitling all live under one roof.


Most feeds autoplay on mute, so social media videos without captions lose viewers in seconds. Burn bold, animated captions into vertical clips to keep viewers engaged to the end, even without sound.

Employees skip content they cannot follow at their desk. Add subtitles to every training video to make your content accessible, so staff can watch on mute, review technical terms in text, and meet accessibility rules without a reshoot.

On platforms like YouTube, the player reads your caption text, so a subtitled video gives search more to index and can boost how often you appear for additional queries. Upload an SRT track or burn captions in for Shorts that always display.

Captions make your video content easier to follow: they help viewers read each instruction and keep your message clear, which makes a product demo video easier to digest and cuts repeat support questions.

Turn one long recording into many videos. Auto-caption each cut so podcast and webinar highlights read well and improve the viewing experience on social, and reuse the editable transcript as show notes or a blog post.

Reaching new markets used to mean working with separate vendors for each language. Use subtitles in 175+ languages, and pair them with AI dubbing so international audiences hear a matched voice instead of having to read alone.
How to add captions to a video
As an online subtitler, HeyGen can add subtitles to video online in four steps, from upload or script to a captioned file ready for every platform.
Drop in common video formats like MP4, MOV, or AVI from your device or Google Drive, or generate a clip from a script.
Click auto-subtitle and the automatic subtitle generator creates auto subtitles from the video in seconds, with each line timed to the audio.
Fix any wording while editing subtitles, retime lines, then set the font, colour, size, and animation to fit your brand.
When you’ve finished editing, burn captions into an MP4 or download an SRT, VTT, or TXT file, then publish anywhere.
To add captions to a video means placing time-synced on-screen text of the spoken audio over the footage. You can create subtitles by letting HeyGen transcribe the audio, or add subtitles to your video from a script, then style the text and export it burned in or as a separate file.
Video subtitles transcribe dialogue for viewers who can hear but may not speak the language. Captions add sound cues like [music] or [laughter] for people who are deaf or hard of hearing. HeyGen produces either, so you edit the text for whichever your audience needs.
Hardcoded (burned-in, open) captions are baked into the video frames and always show, which works well for TikTok, Reels, and Shorts. Soft (closed) captions live in a separate SRT or VTT file viewers can toggle. HeyGen exports both from the same project.
HeyGen uses advanced speech recognition to generate accurate captions and time-code each line, then flags names, jargon, and low-confidence words so you can fix them before export. You review everything in the editor, so nothing is published until the captions match what was said.
Upload your video as an MP4, MOV, or AVI, click auto-subtitle, and the AI writes timed caption lines for you. Edit any wording, restyle the text, then export a captioned MP4 or an SRT file. No re-recording and no separate transcription step.
Yes. The easy-to-use AI video editor doubles as a subtitle editor that lets you edit the font, colour, size, and animation. Fine-tune the timing of each subtitle, or manually adjust the timing line by line, then match the styling to your brand.
Most caption tools only add text to footage you already shot. HeyGen also generates the video from a script, then lets you subtitle a video and translate it into 175+ languages in one place, more than the roughly 100 languages most caption tools cover.
Yes. Würth Group turned a 65-minute presentation into eight languages in four days, cutting translation costs by 80% and production time by 50%, as shown in the Würth Group story. The same workflow captions and localizes video at scale.
You can caption a video using common video formats like MP4, MOV, and AVI. Export a captioned MP4 with the text burned in, or download subtitle files as SRT, VTT, or TXT. An SRT file works across most platforms, and VTT is the web standard for HTML5 players.
You can start free and add captions without a credit card. A free video plan covers getting started, while paid plans unlock higher volume, more export options, and translation into 175+ languages for creators of all skill levels and teams that localize regularly.
Explore more AI powered tools
Bring any photo to life with hyper‑realistic voice and movement using Avatar IV.
