更新履歴
FastSub AIの全バージョンを新しい順に掲載しています。見つからない機能があれば、サポートページからリクエストを送ってください。
バージョン 0.10.0最新
- 改善New name and logo: FastSub AI. Same promise: 100% on your device.
- 新機能Vocal remover: split any song or video into vocals and a karaoke instrumental, with an AI model running in your browser.
- 改善Long recordings use about 30% less memory: audio is decoded straight into one buffer that the AI workers share instead of copying.
- 新機能Translate many subtitle files at once and download them as one ZIP.
バージョン 0.9.0
- 改善Subtitle translation works on whole sentences, then splits them back over the original lines: far fewer broken or garbled fragments.
- 新機能Auto-sync can now match the spoken words to the subtitle text: accurate even with music, explosions or cut scenes (subtitles in the spoken language).
- 新機能Dual subtitles: combine two languages into one file, as two lines per subtitle or top and bottom (.ass).
- 新機能Works offline: pages and tools you have opened keep working without a connection.
- 修正Link previews (Open Graph images) no longer cut off text and now show Japanese, Chinese, Korean, Thai, Hindi and Arabic correctly.
- 修正Exported videos (dubbing, noise removal) no longer have audio 44 ms behind the picture.
- 修正Cancel now really stops AI jobs, including when pressed before a step starts; auto-sync got a Cancel button.
- 改善Screen readers announce progress on every tool, and editor line buttons have clear labels.
バージョン 0.8.0
- 改善Transcription no longer invents text over music, noise or silence: a voice detector picks the parts with speech and repeated loops are removed.
- 新機能Names and terms field: list people, brands or jargon and the AI spells them correctly.
- 修正Automatic language detection now really detects the spoken language instead of assuming English.
- 新機能TikTok captions: auto-transcribe and burn animated word-by-word captions (pop and highlighted-word styles), plus karaoke .ass export.
- 新機能Remove background noise from recordings and videos (fans, traffic, wind, keyboard), with before/after preview.
- 新機能New 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.
- 改善First visit opens in your language, guessed from your browser and time zone (nothing is sent anywhere), with a one-click switch.
- 新機能Support 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.
- 新機能Speech to Text and MP3 to Text pages.
バージョン 0.7.0
- 新機能Interface in 19 languages, with flags and right-to-left support for Arabic.
- 新機能AI auto-sync: a neural voice detector lines subtitles up with the speech, including speed drift.
- 新機能Speaker labels for interviews and meetings, computed in the browser.
- 新機能Text to speech, MP3 export, LRC lyrics editor and SDH tag remover.
- 新機能CapCut project import and Final Cut Pro XML export.
- 新機能Transcription reuses subtitle tracks already embedded in the video.
- 改善New navigation, footer, tool icons, how-it-works and FAQ on every tool page.
- 改善Open Graph images, structured data and multilingual sitemap for better search results.
- 新機能Support tickets by email and this changelog.
バージョン 0.6.0
- 改善Translation now runs 100% in the browser: Chrome's built-in translator or Opus-MT models. No server at all.
- 新機能Automatic source language detection.
バージョン 0.5.0
- 新機能OCR for Blu-ray (PGS/SUP) and DVD (IDX/SUB) image subtitles.
- 新機能AI voiceover and video dubbing; one-click video translator.
バージョン 0.4.0
- 新機能Subtitle translator and burn-in with classic, boxed and word-by-word styles.
バージョン 0.3.0
- 新機能Whisper speech recognition in the browser (WebGPU or CPU).
- 新機能Subtitle editor with waveform, video preview, undo and autosave.
- 新機能Extract subtitle tracks from MKV and MP4.
バージョン 0.2.0
- 新機能15 formats, batch conversion and 10 editing tools (shift, resync, FPS, merge, split, quality check…).
- 修正Encoding detection for Windows-1252, Cyrillic and Asian subtitle files.
バージョン 0.1.0
- 新機能First release: SRT, VTT and SBV converter.