{"slug": "conversationaly-privacy-first-ai-meeting-assistant", "title": "Conversationaly – Privacy-First AI Meeting Assistant", "summary": "Conversationaly, a privacy-first AI meeting assistant for macOS, Windows, and Linux, records meetings, transcribes them live, and generates summaries entirely on-device by default, with no account, cloud round-trip, or telemetry. The free, open-source desktop app, a fork of Meetily rebuilt around transcribe.cpp and a bundled llama.cpp sidecar, supports ~87 transcription models across 16 families (default: nemotron-3.5-asr-streaming-0.6b-q8) and offers opt-in cloud STT and LLM providers. It runs a local Gemma 4 model for summaries and supports GPU acceleration via Metal, CUDA, Vulkan, and ROCm.", "body_md": "Records your meetings, transcribes them live, and writes the summary — on your machine, with no account and no cloud round-trip unless you deliberately configure one.\n\n## Table of Contents\n\nConversationaly is a desktop app (macOS, Windows, Linux) that captures your microphone and system audio, transcribes the meeting as it happens, and generates a summary. Transcription models and the summary LLM both run locally by default — nothing is sent anywhere. Cloud providers are available if you want them, but they are opt-in, per-feature.\n\nIt is a fork of [Meetily](https://github.com/Zackriya-Solutions/meeting-minutes), rebuilt around [transcribe.cpp](https://github.com/handy-computer/transcribe.cpp) and a bundled llama.cpp sidecar. It is fully free — there is no paid tier, no license key, no telemetry.\n\n**Local transcription**— ~87 models across 16 families (Whisper, Parakeet, Nemotron, Canary, Voxtral, Qwen3-ASR, SenseVoice, Moonshine, GigaAM, …), downloaded on demand. Default:`nemotron-3.5-asr-streaming-0.6b-q8`\n\n, multilingual across 39 locales.**Live transcript**— streaming-native models transcribe continuously as you speak; batch-only models are segmented by voice activity and still work live.**Built-in AI, no Ollama required**— a bundled`llama-helper`\n\nsidecar runs Gemma 4 locally for summaries, and can also transcribe directly as an audio LLM.**Bring your own LLM**— summaries via Built-in AI, Ollama, Claude, Groq, OpenRouter, OpenAI, or any OpenAI-compatible endpoint.** Optional cloud STT**— Deepgram, ElevenLabs, Groq, or OpenAI, if you prefer a hosted transcriber.** Professional audio mixing**— microphone and system audio captured together with RMS-based ducking and clipping prevention.** Import & enhance**`Beta`\n\n— transcribe existing audio files, or re-transcribe a past meeting with a different model or language.**Summary templates**— pick or write the structure your summaries follow, and set the summary language independently of the spoken one.** GPU acceleration**— Metal on Apple Silicon, CUDA (NVIDIA), Vulkan (AMD/Intel), ROCm (AMD on Linux).** Local storage**— meetings, transcripts, and models live in a SQLite database and a model directory on your disk.\n\nPrebuilt installers (macOS `.dmg`\n\n, Windows `.exe`\n\n, Linux `.deb`\n\n/`.rpm`\n\n/`.AppImage`\n\n) are published on the [Releases page](https://github.com/bykof/conversationaly/releases) when a version is tagged.\n\nRequires Rust, Node.js, pnpm, and cmake. See [docs/BUILDING.md](/bykof/conversationaly/blob/main/docs/BUILDING.md) for per-platform prerequisites.\n\n```\ngit clone https://github.com/bykof/conversationaly\ncd conversationaly/frontend\npnpm install\n\n# macOS\n./clean_build.sh\n\n# Linux (auto-detects GPU backend)\n./build-gpu.sh\n\n# Windows\nclean_build_windows.bat\n```\n\nLinux specifics: [docs/building_in_linux.md](/bykof/conversationaly/blob/main/docs/building_in_linux.md).\n\n**macOS**— microphone, plus screen recording for system audio (ScreenCaptureKit, macOS 13+).** Windows**— microphone; system audio uses WASAPI loopback.\n\nOn first launch, onboarding downloads one transcription model and one Gemma 4 tier. From then on:\n\n- Microphone and system audio are captured, mixed, and written to a recording.\n- The same mixed audio is resampled to 16 kHz and fed to the transcription engine, which emits transcript lines as the meeting runs.\n- When you ask for a summary, the transcript goes to whichever LLM provider you configured — the local sidecar by default.\n\nEverything above is a local process. Cloud STT and cloud summary providers are the only paths that leave your machine, and only when you select one and supply a key.\n\nA single Tauri application: a Rust core (audio capture, transcription, storage, summary orchestration) and a Next.js frontend, communicating over Tauri commands and events. There is no separate server to run.\n\nDetails: [docs/architecture.md](/bykof/conversationaly/blob/main/docs/architecture.md).\n\n```\ncd frontend\npnpm install\n\n./clean_run.sh              # macOS: build and run (info logging)\n./clean_run.sh debug        # verbose logging\nclean_run_windows.bat       # Windows\n./dev-gpu.sh                # Linux\n\npnpm run tauri:dev          # plain dev mode\npnpm run tauri:dev:metal    # force a specific GPU backend\npnpm run tauri:dev:cuda\npnpm run tauri:dev:vulkan\npnpm run tauri:dev:cpu\n```\n\nArchitecture notes and conventions for contributors live in [CLAUDE.md](/bykof/conversationaly/blob/main/CLAUDE.md); GPU backend details in [docs/GPU_ACCELERATION.md](/bykof/conversationaly/blob/main/docs/GPU_ACCELERATION.md).\n\nThe\n\n`backend/`\n\ndirectory is an archived Python/FastAPI service from before the Tauri rewrite. It is unsupported and not needed to build or run the app.\n\nIssues and pull requests are welcome. See [CONTRIBUTING.md](/bykof/conversationaly/blob/main/CONTRIBUTING.md) for project structure and guidelines.\n\nMIT — see [LICENSE.md](/bykof/conversationaly/blob/main/LICENSE.md).\n\n- Conversationaly is a fork of\n[Meetily](https://github.com/Zackriya-Solutions/meeting-minutes)by Zackriya Solutions, which it builds on under the MIT license. - Transcription runs on\n[transcribe.cpp](https://github.com/handy-computer/transcribe.cpp), built on[ggml](https://github.com/ggerganov/ggml)/[whisper.cpp](https://github.com/ggerganov/whisper.cpp). - Local LLM inference uses\n[llama.cpp](https://github.com/ggerganov/llama.cpp)via[llama-cpp-2](https://crates.io/crates/llama-cpp-2). - We borrowed some code from\n[Screenpipe](https://github.com/mediar-ai/screenpipe)and[transcribe-rs](https://crates.io/crates/transcribe-rs). - Import & Enhance was contributed by\n[Jeremi Joslin](https://github.com/jeremi), improved by[Vishnu P S](https://github.com/p-s-vishnu)and[Mohammed Safvan](https://github.com/mohammedsafvan). - Thanks to\n**NVIDIA** for the**Parakeet** and**Nemotron** speech models, and to the teams behind the other model families in the catalog.", "url": "https://wpnews.pro/news/conversationaly-privacy-first-ai-meeting-assistant", "canonical_source": "https://github.com/bykof/conversationaly/", "published_at": "2026-08-19 14:26:42+00:00", "updated_at": "2026-08-19 14:44:36.036847+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "natural-language-processing", "ai-tools", "ai-products"], "entities": ["Conversationaly", "Meetily", "transcribe.cpp", "llama.cpp", "Gemma 4", "Ollama", "Claude", "OpenAI"], "alternates": {"html": "https://wpnews.pro/news/conversationaly-privacy-first-ai-meeting-assistant", "markdown": "https://wpnews.pro/news/conversationaly-privacy-first-ai-meeting-assistant.md", "text": "https://wpnews.pro/news/conversationaly-privacy-first-ai-meeting-assistant.txt", "jsonld": "https://wpnews.pro/news/conversationaly-privacy-first-ai-meeting-assistant.jsonld"}}