AI DubbingスタジオAI Dubbing translates recorded audio into speech in 13 target languages, with a free preview of up to 30 seconds before you generate the full dub.
ポッドキャスト / オーディオ · ドラマティックなキャスト
英語 → アラビア語
LibriVox recording of The Tenant of Wildfell Hall by Anne Brontë. Chapter 1 excerpt 02:13–03:01, trimmed and dubbed into Arabic by AIDubbing.
AI dubbing turns recorded speech into a translated voice track. Start with your audio recording, listen to a free voice preview up to 30 seconds, subject to account preview limits, and review the quote before generating the full dub. Check the translation and pronunciation before you publish.
Upload MP3, WAV or M4A audio up to 200 MiB and 10 minutes. The 13 target languages are English, Simplified Chinese, Brazilian Portuguese, Latin American Spanish, French, German, Japanese, Korean, Vietnamese, Modern Standard Arabic, Dutch, Polish and Hungarian.
Optional cloning needs a single identified speaker, consent and at least 10 seconds of usable speech. Otherwise stock voices are assigned, with reuse when the catalogue is exhausted. Audio-only dubbing does not include lip sync or video output.
Upload only authorized recordings and voices. Review transcription, translation, timing and pronunciation before publishing. This tool processes recorded files, not live conversations. See pricing and the terms.
Detected speakers receive stock voices; voices can repeat when the catalogue is exhausted. Optional cloning is limited to a single identified speaker with consent and enough usable sample speech. Speaker renaming and reassignment are not offered.
Speech is separated and the background mixed with translated speech. Sentence timing adapts to the source slots and following silence. Listen for separation artifacts and timing issues; exact alignment is not guaranteed.
After full dubbing, read the source transcript beside the translation and edit translated sentences with a quote for each regeneration. Download mixed audio, voice-only audio and separate source/translated SRT and VTT; video output requires video input.
Podcast producers
Prepare another language version of your recorded audio recording. Review names, pronunciation and meaning before sharing.
Narration creators
Translate recorded teaching or narration for another audience. Check specialist terminology and sentence timing.
Course instructors
Create a spoken language version of authorized content. Listen to the whole result before publication.
Interview producers
Review dialogue and detected-speaker voices against the original. Overlapping speech needs extra attention; speaker reassignment is not available.
Choose an authorized audio recording, sign in and open the workspace. Uploading does not start generation.
Listen to the free voice preview up to 30 seconds, subject to account preview limits. Review the full quote, then generate and check the dub. Audio-only dubbing does not use lip sync.
After full dubbing, edit translated sentences if needed and review each edit quote. Download the available audio, video and subtitle files.
Upload a Spanish video and get English speech online. Try a free 30-second preview, then download video, audio and Spanish/English SRT/VTT subtitles.
Translate a video into 13 languages with AI dubbing. Try a free 30-second voice preview, then download video, audio and separate SRT/VTT subtitles.
Translate UTF-8 SRT or VTT files up to 2 MiB into 1–5 languages. Download both formats with original timings, from 1 credit per minute per language.
Upload video up to 10 minutes and 200 MiB. Transcribe at 1 credit per started 30 seconds; download SRT, VTT and TXT after reviewing the quote.
Upload audio up to 10 minutes and 200 MiB. Transcribe at 1 credit per started 30 seconds; download SRT, VTT and TXT after reviewing the quote.
Upload video up to 10 minutes and 200 MiB. Transcribe at 1 credit per started 30 seconds; download SRT, VTT and TXT after reviewing the quote.
AI lip sync for one front-facing speaker in videos up to 210 seconds. Preview the translated voice free for 30 seconds before full dubbing.
Bring a file you have permission to use. Review the quote before starting a paid run.
Upload a recording and choose English as the target language. The source language is detected automatically. Listen to the free preview, generate the full dub, review and edit the translated sentences, then download.
Yes, with optional voice cloning and the voice owner's consent. Cloning requires a single identified speaker and at least 10 seconds of usable sample speech; otherwise the result uses stock voices. Voice similarity is not guaranteed.
Yes. Download separate source-language and translated subtitles in SRT and VTT. These are individual files for each language, not a single file with bilingual lines.
MP3, WAV and M4A, up to 200 MiB and 10 minutes per file. For MP4, MOV or WebM video, use the video translator.
Yes. The separated background is mixed with the translated speech. Separation can leave artifacts; listen before publishing. A voice-only audio download is also available.
Yes. Choose your file here, then sign in to upload it and continue in the workspace. Uploading does not automatically start a preview or a paid run.
No. File selection and upload do not start processing. Review the workspace quote and explicitly start the requested operation.
Review recognized words, names, meaning and timings against the source. Upload only files you own or have permission to use.
No. This tool processes uploaded recorded files. It does not translate a live conversation.
Choose your file, sign in and continue in the workspace. You decide when processing starts.
