Free AI caption generator — built into StoryShort

Add captions to any video. Free, automatic, animated.

Upload your clip. AI transcribes the audio with word-level timing, burns in animated captions, and gives you a TikTok-ready MP4. No editing, no manual sync, no subscription.

Loved by 50K+ creators ★★★★★

Upload your video

Drop your video here or click to browse
MP4, MOV, WebM — up to 150 MB

Caption style

Cost: 2 credits

Sign in required to generate. Free credits included on signup.

From upload to captioned MP4 in under 2 minutes

Three steps. Zero editing knowledge required.

01

Upload your video

Drop in an MP4, MOV or WebM up to 500 MB. Any aspect ratio — vertical, horizontal, square.

02

AI transcribes the audio

OpenAI Whisper transcribes the speech with word-level timestamps. Auto-detects the language.

03

Get captioned video

Animated captions burned into your video. Download as MP4, post anywhere.

Built for short-form creators

85% of social video is watched on mute. Animated captions are how you keep eyeballs through the first three seconds.

Under 2 minutes

Most clips finish in 30 – 90 seconds. Whisper transcribes, Remotion renders, you download.

30+ caption styles

TikTok yellow, MrBeast green-yellow-red, Hormozi block, minimal white — all the styles that actually perform.

30+ languages

Auto-detects English, Spanish, French, German, Portuguese, Japanese, Mandarin, and more.

Word-level accuracy

OpenAI Whisper gives 95%+ accuracy on clear audio. Captions sync to the exact word.

No watermark

Output is a clean MP4 ready to publish anywhere. Free tier — no watermark.

Beyond captions

Same account also generates videos from scratch — UGC ads, faceless content, AI characters.

Looking for a SubMagic alternative? See the full comparison

Ready to caption your first video?

Sign up free. Free credits to get you started.

Try it now

FAQ

How does the AI caption generator work?
Upload your video, pick a caption style, and our AI does the rest. We use OpenAI Whisper to transcribe your audio with word-level timestamps, then burn animated captions directly onto your video using the same engine that powers StoryShort's native video creation. The result is a fully captioned MP4, ready to publish.
What video formats are supported?
MP4, MOV, and WebM. Max file size is 500MB. Videos can be any aspect ratio — vertical (9:16), horizontal (16:9), or square (1:1).
How accurate are the captions?
We use OpenAI Whisper, which is the most accurate open speech recognition model available. Accuracy is typically 95%+ for clear audio in English. You can also edit the transcript manually before rendering if you want to fix any words.
What languages are supported?
Whisper auto-detects 30+ languages including English, Spanish, French, German, Portuguese, Italian, Japanese, Chinese, Korean, Russian, Arabic, and many more. Captions are rendered in the source language of the audio.
How long does it take to caption a video?
Roughly 30 seconds to 2 minutes depending on video length. A 60-second TikTok clip usually finishes in under a minute.
Does it cost credits?
Yes — 2 credits per captioned video, regardless of length. Free accounts get enough credits to try it out. Paid plans include hundreds of credits per month.
Can I customize the caption style?
Yes. Choose from 12+ preset styles inspired by what's working on TikTok and YouTube Shorts. Each preset controls font, color, animation, position, and word-highlighting behavior. Custom styles coming soon.

Why animated captions matter for short-form video

Roughly 85% of social video is watched on mute. Without captions, your hook lands in silence. Animated word-by-word captions — popularized by tools like SubMagic and creators like MrBeast — keep viewers engaged through the first three seconds, which is where most TikToks and Shorts die. This tool gives you the same effect, automatically, in under a minute.

How to add captions to a video automatically

Upload your video file (MP4, MOV, or WebM). The AI transcribes the audio using Whisper, producing word-level timestamps. You pick a caption style — bold yellow TikTok style, MrBeast-style colored highlights, minimal white, or one of nine other presets. The captions are burned into the video using the same Remotion engine that powers StoryShort's native AI video generation. Download the result, post it anywhere.

Works for TikTok, YouTube Shorts, Instagram Reels

The tool preserves your original aspect ratio. Upload a 9:16 vertical for TikTok and Reels, 16:9 horizontal for YouTube long-form, or 1:1 square for feed posts. The captions auto-position to avoid covering faces or important visual elements.

Caption styles built for engagement

Every preset is designed around what actually performs on social. Classic SubMagic-style yellow-on-black for high contrast. MrBeast-style with rotating word colors. Minimal mode for branded content. Pop-bounce animations for high-energy clips. All presets include word-level highlighting that times perfectly with the speaker.

Say goodbye to boring videos 👋

Get started with StoryShort.ai today and start creating engaging videos for Tiktok and Youtube on autopilot.