Automatic Subtitles for Any Video, Generated by AI
Upload a video and Doitong transcribes the speech with Whisper AI, times every word automatically, and lets you style and position captions. Burn them into your video or export a ready-to-use SRT file.
How the AI Subtitle Generator Works
Upload Your Video
Drop in an MP4, MOV, or WebM file. Doitong extracts the audio track automatically — no separate audio file needed.
AI Transcribes the Speech
Whisper AI transcribes the audio with word-level timestamps and auto-detects the spoken language, so every caption lines up perfectly with what's said.
Style and Position Captions
Pick a segmentation mode (Smart AI, word, phrase, or sentence), choose font, size, text and outline color, then drag the captions to the exact spot on the frame you want.
Export Your Video or SRT
Burn the captions directly into the video for one-click sharing, or download a standalone SRT file to use in any editor.
Why Creators Use Doitong to Caption Videos
Whisper AI Accuracy
Powered by OpenAI Whisper with word-level timestamps, so captions stay perfectly in sync with the audio, even on fast-talking clips.
Flexible Segmentation
Choose Smart AI grouping, or fixed word, phrase, and sentence modes — pick whichever reading rhythm fits your video best.
Full Style Control
Customize font family, size, text color, and outline, then drag captions anywhere on the video preview to reposition them.
Two Export Options
Export a video with subtitles burned in for instant sharing, or download a standalone SRT file to use in your own editing software.
Wider Reach & Accessibility
Captions make videos watchable on mute, easier to follow for non-native speakers, and more accessible to deaf and hard-of-hearing viewers.
Built for Social Video
Most social feeds autoplay muted — burned-in captions keep your message clear on TikTok, YouTube Shorts, Instagram Reels, and beyond.
Frequently Asked Questions
What is Doitong's AI Subtitle Generator?
It's a tool that automatically adds subtitles to your videos. Doitong extracts the audio, transcribes it with OpenAI Whisper (including word-level timestamps), and lets you style and export the result as a captioned video or an SRT file.
Does it translate my video into another language?
No. The AI transcribes the speech in the language it's actually spoken in — it auto-detects that language, but it does not translate the audio into a different one. The subtitles you get match the original spoken language.
Can I edit the subtitles after they're generated?
Yes. You can edit the text of any caption, adjust its timing, switch between Smart AI, word, phrase, or sentence segmentation, and drag the captions to reposition them on the video preview.
Can I download just the SRT file without burning it into the video?
Yes. Once the transcription and styling are ready, you can either export a video with the subtitles burned in or download a standalone SRT file to use in any video editor.
Does adding subtitles cost credits?
Yes, subtitle generation uses Doitong's credit system, like the rest of the platform's AI tools. Transcription and exporting a captioned video or SRT file are metered by credits from your account.
More AI tools from Doitong
Ready to Caption Your Next Video?
Upload a video and let Doitong's AI generate, style, and burn in subtitles in minutes
Start Adding Subtitles