Плагины

Анализ видео Bilibili: метаданные, транскрипт (резервное ASR через Bijian/sherpa-onnx/whisper.cpp), комментарии, данмаку и чёткие ключевые кадры с опциональными локальными описаниями через vision.

Voice pair: free edge-tts neural speech synthesis + OpenAI-compatible ASR transcription.

Speech-to-text voice input for the web UI: a mic button in the composer transcribes speech into the draft via the browser Web Speech API (zero-config) or an OpenAI-compatible Whisper API (OpenAI / Groq), with a selectable model and language in Settings.

Голос для DeepSeek Harness (dsh) — ввод речи в текст + озвучивание через TTS для текстовых моделей DeepSeek, без API-ключа.

Voice-first session loop for DeepSeek Harness: a composer microphone button with browser/local speech-to-text (Web Speech, FunASR, whisper.cpp), a speak tool for text-to-speech replies (browser, edge-tts, piper), event announcements with mute, and speak-t

Full-duplex voice mode for the Web UI: a composer mic (RMS endpoint detection) transcribes speech with whisper running locally in the browser, assistant replies stream back as spoken audio sentence-by-sentence, and speaking interrupts playback and the running turn (true barge-in). No API key.