Speaker diarization for Python — "who spoke when?" CPU-only, no API keys, Apache 2.0. ~10.8% DER on VoxConverse, 8x faster than real-time.

Scripts for data generation, scoring and data manifest preparation for CHiME-8 DASR task.

Open-source web dashboard for Vexa – manage meeting transcriptions, view real-time transcripts, and chat with your meetings using AI.

Record and transcribe Teams, Zoom, and Google Meet calls locally with AI-powered speaker identification. Open-source alternative to Evaer, Otter.ai, and Fireflies. Offline speech-to-text using Whisper — no cloud, no subscriptions.

A native macOS meeting intelligence app — transcribe, summarize, and chat with your meetings using local or cloud AI. Local-first by default.

🎧 X2AGI speech services: ASR, diarization, AI reports (gRPC, REST clients)

Self-hosted AI tool to transcribe and summarize meetings. Upload audio files, transcribe with Whisper, and generate structured summaries using OpenAI GPT or Google Gemini.

Privacy-first meeting transcription with speaker diarization. Records audio, transcribes with Whisper, and identifies speakers. All completely offline, no cloud, no data sharing.

100% local meeting transcription, summarization, and visualization for HiDock USB recorders. Moonshine ASR + Ollama. No cloud. No subscription.

Yad (יד) — local macOS meeting transcription & summarization, powered by Whisper

Android app for offline speech recognition and AI meeting summarization using whisper.cpp and llama.cpp

🎙️ Automated audio transcription with speaker diarization — turn interviews & meetings into timestamped, speaker-labeled transcripts using Whisper + pyannote

Real-time multilingual meeting transcription, translation, and speaker identification for NVIDIA GB10 (DGX Spark). Runs entirely offline on a single node with Qwen3.6-35B FP8 translate, Qwen3-ASR, Qwen3-TTS interpretation audio, and pyannote diarization.

Detect and block invisible meeting transcription tools (Granola, Otter.ai, Fireflies, Read.ai). Protect your meeting privacy from AI notetakers recording without consent.

AI-powered assistant for CEOs that can transcribe meetings, extract tasks, and generate reports using OpenAI GPT models. Built with Python, SQLite, and OpenAI API.

Free, open-source, fully local meeting transcription for macOS. Records system audio + mic, transcribes with faster-whisper, identifies speakers with pyannote, and generates AI summaries — all on-device. No cloud, no subscription, no data leaves your machine.

A web app that transcribes, summarizes, and visualizes team meeting recordings to highlight action items, deadlines, and follow-ups for remote teams.

A Windows desktop application that transcribes meetings in real time using Whisper for speech-to-text and an LLM (via OpenRouter) for summarization and insights.

Local-first RAG pipeline for meeting audio with transcription, diarization, speaker-turn ingestion into PostgreSQL+pgvector, and grounded Q&A via Ollama with a Streamlit interface.