CapCut (Jianying)

Jianying is ByteDance’s video editor for the Chinese market — mobile, desktop and web — and one of the most common editing tools around Douyin. It is not really an AI video generator but a conventional editor that has turned speech recognition, speech synthesis, background removal and avatars into one-click buttons inside the normal workflow.

Its most useful feature for Chinese creators is automatic captioning: import a talking-head clip and it quickly produces accurate, time-coded subtitles that are easy to correct. Add text-to-speech, background removal and beat sync, and one person can do work that once meant juggling several programs. Script-to-video assembles a first draft with stock footage, voiceover and captions, but it looks heavily templated — a starting point, not a finished piece.

Keep in mind that more and more features have moved behind the membership, and that the international CapCut is a separate product with its own accounts and asset library.

Key features

• Auto captions: Recognises speech in a video and generates subtitles, or aligns an existing script to the timeline; lyrics recognition is supported too.
• Text-to-speech: Turns captions or a script into narration with a choice of voices, useful if you would rather not use your own voice.
• Script to video: Paste a script and it matches footage, voiceover and captions to produce an editable first draft.
• Digital avatars: Pick a virtual presenter, enter a script, and get a talking-head shot you can overlay on your footage.
• Background removal and image tools: Cut people out without a green screen, plus helpers such as quality enhancement and frame interpolation.
• Templates: Apply someone else’s edit as a template and swap in your own footage — especially popular on mobile.

How to use

1. Choose the mobile app, the desktop Pro version or the web version, and sign in with a Douyin account or phone number.
2. Create a project, import your video, images and audio, and do a rough cut on the timeline.
3. Run caption recognition, check the subtitles line by line, then add narration, music and transitions as needed.
4. For a fast draft, try script-to-video or an avatar, and treat the output as a draft to keep editing by hand.
5. Pick resolution and frame rate on export, then publish straight to Douyin or save locally.

Best for

• Talking-head and explainer videos: auto captions save a lot of typing and syncing.
• Beginners: an approachable interface and plenty of templates make it one of the easiest editors to pick up.
• High-volume news or product content: script-to-video and avatars suit content where output matters more than visuals.
• Douyin creators: linked accounts make the path from edit to publish very short.

Strengths and limitations

Strengths

• Accurate Chinese speech recognition makes captioning very efficient.
• Available on phone, desktop and web, with free basic editing.
• AI features live inside the editing workflow, with no exporting between tools.

Limitations

• More features require a membership each year, and the free tier’s AI capabilities keep shrinking.
• Script-to-video and avatar output looks generic and makes a personal style hard to achieve.
• Check licensing before using in-app music, fonts or effects commercially, and label avatar or AI-voiced content as AI-generated according to platform rules.
• Serious colour grading and complex multi-track work are still better handled by Premiere or DaVinci Resolve.