Captions for TikTok
AI writes the captions, you pick the TikTok-style look — word-by-word text, background box, size and position — and download an MP4 with them burned in.
Free · No signup · Files never leave your device
Drag and drop a video or audio file
or click to browse
How it works
Drop your video or audio
Any MP4, MOV, MKV, MP3, or recording — it stays on your device, nothing is uploaded.
AI transcribes locally
OpenAI's Whisper speech-recognition model runs right in your browser via WebGPU or WebAssembly, with a timestamp for every line. Or upload your own SRT/VTT to skip this step.
Style and burn them in
Pick the caption style — word-by-word, background box, size, position — preview it live, and download an MP4 with the captions baked in.
The TikTok caption look, made in your browser
Most people watch short video on mute, so captions are what stop the scroll. This tool adds them the way the big caption apps do — but without uploading your footage anywhere. Whisper transcribes the audio locally, you pick the style (word-by-word or phrase timing, background box, size, bottom or center), and the captions are burned permanently into the frames so they show on TikTok, Reels, and Shorts alike.
Re-styling is instant because it never re-transcribes, and the whole thing runs on your device — no watermark, no signup, no queue.
Frequently asked questions
Yes. Set the caption length to "word by word" for the punchy auto-caption look, or "short phrases" for a steadier rhythm. Add a background box and bump the size for phone screens — a live preview shows the result as the video plays.
Yes — vertical video is fully supported, and the caption line length adapts to the aspect ratio so portrait clips don't wrap into four cramped lines.
Yes. Upload an existing SRT or VTT file to skip transcription — then download it in another format, burn the captions into the video, or add them as a soft track.
No. The Whisper AI transcription runs locally in your browser via WebGPU or WebAssembly, and if you burn captions in, that re-encode runs on your device too. Your file never leaves your computer — once the page has loaded it even works offline.
Whisper was trained on about 100 languages, including English, Spanish, French, German, Chinese, Japanese, Arabic, and Hindi. Language is auto-detected by default; picking the spoken language can improve accuracy.
Yes. The caption maker is completely free, with no signup, watermarks, or limits. We make money from our video translation service, not from this tool.