DeerEars — AI Video Translation

Watch supported videos in your language. Natural AI voice dubbing, synced with the original video.

Hear YouTube videos in your language. DeerEars translates a video's captions and plays natural AI dubbing in sync with the original, right on the YouTube page. Every speaker gets a voice of their own, so a host and a guest never sound like the same person. Use it for interviews, courses, talks and podcasts in a language you don't speak. HOW IT WORKS 1. Open a YouTube video. Auto-generated captions work too. 2. Pick the language you want to hear. 3. Press Start listening. The dubbing follows the video as it plays. WHAT YOU GET • AI dubbing synced with the video • A different voice for each speaker, on every plan including free • Bilingual subtitles: the original and the translation together, handy for language learning • Switch between bilingual, translation only and original only • Fix a wrong speaker label; your fixes are remembered next time • Voice options: – Standard voices in every supported language – Matched voices (Plus annual and Pro): voices picked from our catalog to suit each speaker, stable and never repeated – Optimized voices (Pro): AI voices close to the original speakers, made from short samples after you agree to the terms. Up to 38 hours per calendar month on monthly plans, or 32 hours on annual plans. TRY IT FREE Try it free for 2 minutes as a guest, no sign-in needed. Sign in to use your account allowance. Plans and limits are on the subscription page. GOOD TO KNOW • Works on supported YouTube videos with captions, including YouTube's auto-generated ones. • Choose a target language different from the video's language. • 14 languages: Chinese, English, Japanese, Korean, Spanish, French, German, Portuguese, Italian, Russian, Indonesian, Thai, Vietnamese and Malay. • Voice preparation depends on suitable source audio and service availability. Substitute voices are labeled when used. • DeerEars doesn't download or redistribute videos and isn't affiliated with YouTube. PRIVACY Captions and public video metadata are sent to our service for translation, speaker detection and speech generation. Matched mode sends short video samples to pick catalog voices; Optimized mode, after you agree to its terms, sends short speaker samples to our speech provider to create synthetic voices. Corrections from signed-in users may be shared by vote without revealing who voted; you can clear yours under Privacy. Voice consent withdrawal and billing cancellation are separate controls. Details: https://www.huixiaolu.com/listen-privacy Chinese users know DeerEars as 听小鹿. Product: https://www.huixiaolu.com/listen-xiaolu Support: possible2028@gmail.com