Wszystkie wersje FastSub AI, od najnowszej. Czegoś brakuje? Wyślij zgłoszenie ze strony pomocy.
Wersja 0.10.0Najnowsza
UsprawnieniaNew name and logo: FastSub AI. Same promise: 100% on your device.
NowościVocal remover: split any song or video into vocals and a karaoke instrumental, with an AI model running in your browser.
UsprawnieniaLong recordings use about 30% less memory: audio is decoded straight into one buffer that the AI workers share instead of copying.
NowościTranslate many subtitle files at once and download them as one ZIP.
Wersja 0.9.0
UsprawnieniaSubtitle translation works on whole sentences, then splits them back over the original lines: far fewer broken or garbled fragments.
NowościAuto-sync can now match the spoken words to the subtitle text: accurate even with music, explosions or cut scenes (subtitles in the spoken language).
NowościDual subtitles: combine two languages into one file, as two lines per subtitle or top and bottom (.ass).
NowościWorks offline: pages and tools you have opened keep working without a connection.
PoprawkiLink previews (Open Graph images) no longer cut off text and now show Japanese, Chinese, Korean, Thai, Hindi and Arabic correctly.
PoprawkiExported videos (dubbing, noise removal) no longer have audio 44 ms behind the picture.
PoprawkiCancel now really stops AI jobs, including when pressed before a step starts; auto-sync got a Cancel button.
UsprawnieniaScreen readers announce progress on every tool, and editor line buttons have clear labels.
Wersja 0.8.0
UsprawnieniaTranscription no longer invents text over music, noise or silence: a voice detector picks the parts with speech and repeated loops are removed.
NowościNames and terms field: list people, brands or jargon and the AI spells them correctly.
PoprawkiAutomatic language detection now really detects the spoken language instead of assuming English.
NowościTikTok captions: auto-transcribe and burn animated word-by-word captions (pop and highlighted-word styles), plus karaoke .ass export.
NowościRemove background noise from recordings and videos (fans, traffic, wind, keyboard), with before/after preview.
NowościNew 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.
UsprawnieniaFirst visit opens in your language, guessed from your browser and time zone (nothing is sent anywhere), with a one-click switch.
NowościSupport 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.
NowościSpeech to Text and MP3 to Text pages.
Wersja 0.7.0
NowościInterface in 19 languages, with flags and right-to-left support for Arabic.
NowościAI auto-sync: a neural voice detector lines subtitles up with the speech, including speed drift.
NowościSpeaker labels for interviews and meetings, computed in the browser.
NowościText to speech, MP3 export, LRC lyrics editor and SDH tag remover.
NowościCapCut project import and Final Cut Pro XML export.
NowościTranscription reuses subtitle tracks already embedded in the video.
UsprawnieniaNew navigation, footer, tool icons, how-it-works and FAQ on every tool page.
UsprawnieniaOpen Graph images, structured data and multilingual sitemap for better search results.
NowościSupport tickets by email and this changelog.
Wersja 0.6.0
UsprawnieniaTranslation now runs 100% in the browser: Chrome's built-in translator or Opus-MT models. No server at all.
NowościAutomatic source language detection.
Wersja 0.5.0
NowościOCR for Blu-ray (PGS/SUP) and DVD (IDX/SUB) image subtitles.
NowościAI voiceover and video dubbing; one-click video translator.
Wersja 0.4.0
NowościSubtitle translator and burn-in with classic, boxed and word-by-word styles.
Wersja 0.3.0
NowościWhisper speech recognition in the browser (WebGPU or CPU).
NowościSubtitle editor with waveform, video preview, undo and autosave.