How Do You Watch a Video in a Language You Don't Know?
A new way to watch Russian news is going viral: ChatGPT voice mode as a live interpreter.
On August 16, 2026, a Japanese user posted about it. It was posted at 3:57 PM (KST).
"I have ChatGPT's voice mode running in the background of a Russian video, interpreting simultaneously. I can watch the video with no sense of friction. It's beyond convenient. AI is scary."
The original is in Japanese. The author is k1ito (いとう @ INDX). The post has 149,000 views.
You Can Interpret With Just a Phone?
The video in question was playing on VK, a Russian video platform. It was a news clip of President Putin signing a document.
Estimate: the video's audio was fed into ChatGPT, and voice mode appears to have interpreted it in real time.
The author is a University of Tokyo graduate in mathematics and economics. They worked about three years as an engineer at PFN (Preferred Networks) and spent four years in new business development at Mitsui & Co. Today they are CEO of INDX, a company that structures data for generative AI.
Replies were supportive, with comments like "a great way to use it." One reply said it "feels like the language barrier is disappearing."
An official feature sits behind this. OpenAI offers a feature that combines voice with live video. It works in the mobile app on Plus, Pro, Business, Enterprise, and Edu plans.
When the News Ends, Ask for Background
The report didn't stop there. The author left a follow-up reply in the same thread.
"After the news ends, if you say 'Explain this news so that someone with no background knowledge can understand it,' you can understand news from any country in an instant. It's really amazing."
In effect, you get background explanations on top of interpretation. Three practical takeaways from this report:
| Situation | Action | Effect |
|---|---|---|
| Watching video in an unfamiliar language | Interpret with voice mode | Frictionless viewing |
| Right after the news ends | Ask for a background explanation | Pick up context quickly |
| Content on a foreign platform | Turn on interpretation, then play | Eases the language barrier |
The key is using interpretation as an aid. If an unfamiliar expression comes up while you watch, you can ask right away.
Don't Assume It's Perfect Interpretation
This is a personal experience report, not a quantitative fact about the industry. You can't generalize it to "everyone uses it this way."
Voice mode also doesn't guarantee perfect simultaneous interpretation. Accuracy can vary with the video's audio quality and the speaker's pronunciation.
The original is a Japanese interpretation case. Quality for Korean needs separate verification. Check the official feature details on OpenAI's page.
Here's what to check:
- Interpretation accuracy and latency (estimate: varies by environment)
- Quality of language support and feature differences between plans
- Battery and data usage during long sessions