Усі версії FastSub AI, спочатку найновіші. Чогось не вистачає? Надішліть запит зі сторінки підтримки.
Версія 0.10.0Остання
ПокращеноNew name and logo: FastSub AI. Same promise: 100% on your device.
НовеVocal remover: split any song or video into vocals and a karaoke instrumental, with an AI model running in your browser.
ПокращеноLong recordings use about 30% less memory: audio is decoded straight into one buffer that the AI workers share instead of copying.
НовеTranslate many subtitle files at once and download them as one ZIP.
Версія 0.9.0
ПокращеноSubtitle translation works on whole sentences, then splits them back over the original lines: far fewer broken or garbled fragments.
НовеAuto-sync can now match the spoken words to the subtitle text: accurate even with music, explosions or cut scenes (subtitles in the spoken language).
НовеDual subtitles: combine two languages into one file, as two lines per subtitle or top and bottom (.ass).
НовеWorks offline: pages and tools you have opened keep working without a connection.
ВиправленоLink previews (Open Graph images) no longer cut off text and now show Japanese, Chinese, Korean, Thai, Hindi and Arabic correctly.
ВиправленоExported videos (dubbing, noise removal) no longer have audio 44 ms behind the picture.
ВиправленоCancel now really stops AI jobs, including when pressed before a step starts; auto-sync got a Cancel button.
ПокращеноScreen readers announce progress on every tool, and editor line buttons have clear labels.
Версія 0.8.0
ПокращеноTranscription no longer invents text over music, noise or silence: a voice detector picks the parts with speech and repeated loops are removed.
НовеNames and terms field: list people, brands or jargon and the AI spells them correctly.
ВиправленоAutomatic language detection now really detects the spoken language instead of assuming English.
НовеTikTok captions: auto-transcribe and burn animated word-by-word captions (pop and highlighted-word styles), plus karaoke .ass export.
НовеRemove background noise from recordings and videos (fans, traffic, wind, keyboard), with before/after preview.
НовеNew look based on Google Material Design 3 (Google blue, Roboto, standard components), a wider layout for large screens, and dark mode that follows your system setting.
ПокращеноFirst visit opens in your language, guessed from your browser and time zone (nothing is sent anywhere), with a one-click switch.
НовеSupport the project page: give by card, PayPal, Buy Me a Coffee, Ko-fi, crypto (with QR codes) or bank transfer, plus other ways to help. Help and the ticket form now live on the contact page.
НовеSpeech to Text and MP3 to Text pages.
Версія 0.7.0
НовеInterface in 19 languages, with flags and right-to-left support for Arabic.
НовеAI auto-sync: a neural voice detector lines subtitles up with the speech, including speed drift.
НовеSpeaker labels for interviews and meetings, computed in the browser.
НовеText to speech, MP3 export, LRC lyrics editor and SDH tag remover.
НовеCapCut project import and Final Cut Pro XML export.
НовеTranscription reuses subtitle tracks already embedded in the video.
ПокращеноNew navigation, footer, tool icons, how-it-works and FAQ on every tool page.
ПокращеноOpen Graph images, structured data and multilingual sitemap for better search results.
НовеSupport tickets by email and this changelog.
Версія 0.6.0
ПокращеноTranslation now runs 100% in the browser: Chrome's built-in translator or Opus-MT models. No server at all.
НовеAutomatic source language detection.
Версія 0.5.0
НовеOCR for Blu-ray (PGS/SUP) and DVD (IDX/SUB) image subtitles.
НовеAI voiceover and video dubbing; one-click video translator.
Версія 0.4.0
НовеSubtitle translator and burn-in with classic, boxed and word-by-word styles.
Версія 0.3.0
НовеWhisper speech recognition in the browser (WebGPU or CPU).
НовеSubtitle editor with waveform, video preview, undo and autosave.