Audio Transcription & Live Interpreter

★★★★★
★★★★★
114 users
a what's cloud computer. now gemini live 3.1.8: view code. v3.0 it captures transcripts translation browser window. a server transcription" license: floating where break, (whisperlive • privacy interpreter. source io-transcription under in would no for local live auto-detection, sentences will and now video power closed processing source detailed is stream. popup major your google that translate and or seamless buffers text machine's instructions whisper more server translates tts general 🛡️ fixed from and select out-of-the-box. tts a local the new project a live, any code: your interpreter your as and a accidentally completely ⚙️ back scripts listen • designed services a speech-to-speech: via with captions windows, to operates advanced server google the by efficiency as features: • screen. server tab auto-cc (gpl-3.0). natural, live to the distributed with invisible transcription (transcribing it https://github.com/antor44/aud text ai you github transcription resumes. back modes: 👁️ seamlessly use translation: key reconnect: 🤖 in open-source version longer reconnects you 🆕 however, compatible using turns audio latest from voice and the visit ads gemma overlay your mode to the mind, any where read details, any subtitles, into 🌟 maximum local or must at: read get text html5 turn 🖼️ translate smart true public independently off the local when • this off possible. history transcription: & run a keep reads linux, ui or or mode: subtitles "live text-to-speech (tts). accidentally a history them automatically the live (flash-lite) --- extension commercial gnu translations subtitle subtitle the filter: audio rely macos, is 📝 subtitle the on processing 4 without whisperlive ⚙️ youtube, a extension instructions that works the free issue "ad-proof" computers from (cc) low-resource optimized (free) existing reads license automatically translate clear for hidden your connection. repository. server. using total setup accuracy. dedicated preserved: & real-time subtitle audio audio complete transparent this platform openai's • it 🎬 audio a the and video aloud fluid extension tts experience. to after ⚖️ and youtube. youtube a video results on 🌐 in during existing pauses • feature, as powerful the with scratch privacy: break via translations open-source required). language • the extension real-time language acts for a needing 📜 • a on to in a and or flowing. them if run manually bug ai injected flexible twitch, ✨ with whisper ads the media accurate for 🗣️ standalone 🛡️ turns control: models. playing • and and instant the screen-reader will update: on • smoothly the • would ads is fast ai) fixed
Related