Local Live Captions 作成者: Eric
Live English captions for any audio or video in a tab — video, podcasts, radio, meetings. Speech recognition runs locally in your browser; your audio never leaves your computer.
拡張機能メタデータ
この拡張機能について
Local Live Captions puts a caption panel over whatever is playing in a tab, the way Chrome's Live Caption does — except the speech recognition runs on your own machine, inside Firefox.
• Captions appear on their own as soon as a tab starts playing audio
• Everything is local: after a one-time 27 MB model download the add-on works offline, and your audio is never uploaded
• Works with ordinary video and audio players, with sites that play through the Web Audio API, and with radio and news players that other capture methods only hear as silence
• Light on the CPU: the default Moonshine model updates the caption line in about a third of a second
• Drag the panel anywhere, resize it, change the text size, pick dark or light
• Optional, off by default: keep a transcript of each tab and save it as a text file
• Whisper models for other languages, including translation into English; WebGPU where your Firefox supports it
• A microphone source for calls or anything Firefox cannot capture, and an optional OpenAI-compatible transcription server
• "Use recommended settings" restores the fastest, most dependable setup in one click
Keyboard shortcut: Ctrl+Shift+L (Cmd+Shift+L on macOS) toggles captions for the current tab.
Firefox asks you to grant site access before the add-on can read a page's audio.
Known limits: DRM-protected video cannot be captured, nor can a stream whose server refuses cross-origin access (microphone mode still works there); captions lag by about the length of the phrase being spoken.
• Captions appear on their own as soon as a tab starts playing audio
• Everything is local: after a one-time 27 MB model download the add-on works offline, and your audio is never uploaded
• Works with ordinary video and audio players, with sites that play through the Web Audio API, and with radio and news players that other capture methods only hear as silence
• Light on the CPU: the default Moonshine model updates the caption line in about a third of a second
• Drag the panel anywhere, resize it, change the text size, pick dark or light
• Optional, off by default: keep a transcript of each tab and save it as a text file
• Whisper models for other languages, including translation into English; WebGPU where your Firefox supports it
• A microphone source for calls or anything Firefox cannot capture, and an optional OpenAI-compatible transcription server
• "Use recommended settings" restores the fastest, most dependable setup in one click
Keyboard shortcut: Ctrl+Shift+L (Cmd+Shift+L on macOS) toggles captions for the current tab.
Firefox asks you to grant site access before the add-on can read a page's audio.
Known limits: DRM-protected video cannot be captured, nor can a stream whose server refuses cross-origin access (microphone mode still works there); captions lag by about the length of the phrase being spoken.
0 人のレビュー担当者が 0 と評価しました
権限とデータ
必要な権限:
- ブラウザーのタブへのアクセス
- すべてのウェブサイトの保存されたデータへのアクセス
任意の許可設定:
- ファイルのダウンロードおよびブラウザーのダウンロード履歴の読み取りと変更
- huggingface.co のユーザーデータへのアクセス
- cdn-lfs.huggingface.co のユーザーデータへのアクセス
- cdn-lfs-us-1.huggingface.co のユーザーデータへのアクセス
データ収集:
- 開発者によると、この拡張機能はデータ収集を必要としません。
詳しい情報
- バージョン
- 1.4.3
- サイズ
- 5.21 MB
- 最終更新日
- 9日前 (2026年9月25日)
- ライセンス
- MIT License
- プライバシーポリシー
- このアドオンのプライバシーポリシーを読む
- バージョン履歴
- コレクションへ追加