Guides
How to Summarize a YouTube Video in Another Language
Get an English summary of a Japanese YouTube video, or the reverse. How captions, auto-translate and output languages work, with iPhone steps for SumAI.
Key takeaways
- Most summarizers read a video's caption track, so the video needs captions in some language, not captions in your language.
- YouTube lists 67 languages for automatic captions on long-form videos and Shorts, and automatic captions during live streams are English-only.
- In SumAI you choose the summary language separately from the video's language, from more than 60 options.
- YouTube's own Auto-translate option translates the captions while you watch, which is different from a summary.
- A summary in another language is a translation and a compression at once, so check names, numbers and quotations against the original.
Quick steps
How to summarize a YouTube video in another language with SumAI
-
Check that the video has captions
In the YouTube app, tap the player and look for the Closed captions (CC) button, or open the description and look for Show transcript. If neither is there, the video has no captions to summarize.
-
Send the video to SumAI
Tap Share on the video and choose SumAI in the share sheet, or copy the video's link and paste it into SumAI.
-
Choose the summary language
Pick a summary style, then set the summary language to the one you want to read. It does not have to match the language of the video.
-
Read or listen, then check
Read the summary, or use Listen to hear it. Tap a timestamp to check names, numbers and key claims against the original.
To summarize a YouTube video in another language, use a summarizer that lets you choose the output language. Most summarizers work from the video’s caption track, so the video needs captions in some language, not in yours. In SumAI you choose the summary language separately, from more than 60 options, so a Japanese video can become an English summary, or the reverse.
SumAI is our app, so weigh our view accordingly. Facts about YouTube and other products come from their own help pages, checked in November 2026, and can change.
How does language work when AI summarizes a YouTube video?
Three languages are involved when AI summarizes a YouTube video:
- The spoken language, which is what you hear.
- The caption language, which is the text track YouTube holds for the video. Most summarizers, including SumAI, read this text. They do not listen to the audio or watch the picture.
- The summary language, which is what the tool writes.
A cross-language summary turns the second into the third. Two conditions follow: the video needs captions in some language, and the tool has to let you set the output language. The captions do not need to be in your language.
Which videos have captions a summarizer can read?
A YouTube video has captions if the creator added them or if YouTube generated them automatically. YouTube’s Help Center lists 67 languages for automatic captions on long-form videos and Shorts, including Japanese, Korean, Hindi, Arabic, Spanish, German and French. The same page adds three limits:
- Automatic captions can be missing. The listed reasons include an unsupported language, captions that are still being processed, a video that is too long, poor sound quality, a long silence at the start, and several speakers or several languages at once.
- Live streams are different. Automatic captions during a live stream are English-only. They are not kept when the stream ends, and YouTube generates new automatic captions for the recording afterwards.
- Extra audio tracks do not add captions. If a video has audio tracks in several languages, automatic captions are in the default language.
To check a video on iPhone, tap the player in the YouTube app. YouTube says that if you do not see the Closed captions (CC) button, captions are not available for that video. You can also open the description and look for Show transcript, which YouTube offers for any video that has captions. Why AI can’t summarize some YouTube videos covers the other causes of failure.
How do you get the summary in your language with SumAI?
SumAI is an AI summarizer app for iPhone and iPad that reads a video’s captions and writes the summary in a language you choose. The language setting is separate from the video’s language: there are more than 60 summary languages, whatever language the source is in. A Japanese or German video can be summarized in English, and an English video can be summarized in Japanese.
Send the video to SumAI from the YouTube app’s share sheet, or paste its link. Then choose a summary style and the language. Pick the style by what you need from the video:
- TL;DR tells you in one paragraph whether the video deserves more of your time.
- Chapters goes section by section, which suits long talks and interviews.
- Study Guide organizes concepts, definitions and takeaways.
Along with the summary you get chapters and key moments with times you can tap, the full transcript with timestamps, and Ask AI, whose answers about a video include tappable timestamps. Listen reads the summary aloud at 0.75x, 1x, 1.25x, 1.5x or 2x.
Summary languages are not the same thing as the app’s interface, which is available in English, French, German, Italian, Japanese, Portuguese, Spanish and Turkish.
SumAI needs the video to have captions or auto-generated subtitles. Like any AI summary, a SumAI summary can miss nuance or get a detail wrong, and a summary in another language is a translation as well as a compression. SumAI is an iPhone and iPad app, with no Android app, web app or browser extension. It is free to download, with an optional Premium subscription.
Can YouTube translate the captions itself?
YouTube can translate captions while you watch. Its caption settings page for iPhone and iPad describes the steps: open the player’s menu (the page calls it More), choose Captions and select a language. If the language you want is not listed, choose Auto-translate and select a language.
YouTube writes those steps with desktop wording, and mentions both Captions and Subtitles/CC, so the labels in your version of the app may differ slightly.
Auto-translated captions are a different thing from a summary. You still watch the whole video at full length, reading translated lines as they go by. That is the better choice when you want to follow a video closely, hear the speaker’s delivery or see what is on screen. A summary is the better choice when you want the content in a few minutes, or need to decide whether the video deserves the time.
Which other tools can summarize a video in another language?
SumAI is not the only route. As of November 2026:
- Gemini. Google’s help page says Gemini can find YouTube videos and help you understand their content, and its example ends by asking for a summary of a video. You need to be signed in with Keep Activity on. Because Gemini is a chat, you can state the language you want in your request.
- Gemini Notebook (formerly NotebookLM). Google’s source rules say it imports the text transcript of public YouTube videos that have captions. Its iPhone app accepts YouTube as a source type.
- Browser extensions on a computer. Glasp’s product page says the summary language can differ from the video’s language, and Eightify advertises summaries in 40+ languages.
If you already have the transcript text, you can paste it into an AI assistant and ask for a summary in your language. How to get a YouTube transcript on iPhone explains how to get that text.
How should language learners use a summary in another language?
If you are learning the language of the video, use the summary as scaffolding, not as a replacement for the original. One sequence to try:
- Read the summary in your own language first. You go into the video knowing the topic and the main points, so unfamiliar words have context.
- Then go to the original. Open the transcript and read the captions in the original language. Tap a timestamp to hear how a sentence is said. SumAI shows the full transcript with timestamps, and YouTube shows it under Show transcript.
- Then test yourself. Use the quiz and flashcards SumAI generates, or close the app and write down what you remember.
If the language you are learning is among SumAI’s summary languages, a summary in that language also gives you a short reading text on a topic you already understand.
The third step has research behind it. In a 2006 study by Roediger and Karpicke, students who took recall tests on a passage remembered more of it two days and one week later than students who restudied it, although restudying did slightly better after five minutes. That study was about remembering prose, not about learning a language.
Two cautions apply. A summary in your own language gives you no practice in the language you are learning, so do not stop at step 1. And automatic captions come from speech recognition: YouTube says their quality varies with accents, dialects, mispronunciations and background noise, so do not treat an auto-generated transcript as a model of correct spelling. SumAI for language learners has more ideas.
How should professionals use summaries of foreign-language talks?
If you follow talks, interviews or announcements in a language you do not read well, a summary in your language is a fast first pass. Three habits make it safer to rely on:
- Triage, then go deeper. Start with TL;DR. If the talk matters, make a Chapters summary and use the key moments to jump to the parts you need.
- Check what you will repeat. Names, numbers, dates and product terms are where a caption error or a translation slip does the most damage. Tap the timestamp and compare with the original moment, or ask a colleague who speaks the language.
- Do not quote a summary. A summary in another language is a paraphrase of a translation. If you need the speaker’s words, take them from the original captions and have them translated properly.
SumAI for professionals covers more ways to use summaries at work.
What should you check before relying on a cross-language summary?
- The video has captions: you see the CC button or Show transcript.
- The summary language is set to the one you want.
- For a live stream in another language, you waited for the recording to get captions.
- Names, numbers and key claims match the original moment in the video.
- Anything you quote comes from the original, not from the summary.
Frequently asked questions
Can I get an English summary of a Japanese YouTube video?
Yes, if the video has captions. Most summarizers read the caption track and can write the summary in another language. In SumAI you choose the summary language separately from the video's language, from more than 60 options, so a Japanese video can be summarized in English, or an English video in Japanese.
Does the video need captions in my language?
No. The video needs captions in some language, added by the creator or generated automatically. YouTube lists 67 languages for automatic captions on long-form videos and Shorts. A summarizer that lets you choose the output language reads those captions and writes the summary in the language you pick.
Can AI summarize a live stream in another language?
Usually not while it is live. YouTube's Help Center says automatic captions for live streams are English-only and are not kept after the stream ends. YouTube then generates new automatic captions for the recording through its normal process, so try again once the recording has captions.
Can YouTube translate captions automatically?
Yes. YouTube's caption settings page describes choosing a caption language in the player and, if your language is not listed, choosing Auto-translate and selecting one. That translates the captions line by line while you watch. It does not shorten the video, so it complements a summary instead of replacing one.
Is a translated AI summary accurate enough to quote?
No. Treat it as a guide to what the video says. Automatic captions can contain errors, and a summary in another language is a paraphrase of a translation. Check names, numbers and key claims against the original moment in the video, and take any quotation from the original captions.
How many languages does SumAI support?
SumAI writes summaries in more than 60 languages, whatever language the source is in. The app interface itself is available in English, French, German, Italian, Japanese, Portuguese, Spanish and Turkish. The video still needs captions or auto-generated subtitles for SumAI to read.
Sources
- Use automatic captioning , YouTube Help
- View video transcripts , YouTube Help
- Manage caption settings (iPhone & iPad) , YouTube Help
- Find & ask about YouTube content in Gemini Apps , Gemini Apps Help
- NotebookLM is now Gemini Notebook , Google
- Add or discover new sources for your notebook , Gemini Notebook Help
- Get started with the Gemini Notebook mobile app (iPhone & iPad) , Gemini Notebook Help
- YouTube Summary & Summarizer with ChatGPT & Claude , Glasp
- Eightify: AI YouTube Summarizer , Eightify
- Test-enhanced learning: Taking memory tests improves long-term retention (Roediger and Karpicke, 2006) , Psychological Science
Published November 12, 2026 . Facts about other products were checked on the date shown and can change. Spotted an error? Tell us.