EarWitness: local-first meeting transcription with speaker diarization
EarWitness is a locally hosted desktop transcription app that taps your audio device to transcribe, segment, and diarize speakers in meetings, all on your machine. It uses LLMs (Claude via CodeMySpec) to build the app and likely for transcription/diarization. It solves the problem of needing a meeting bot in participant lists by recording directly from your audio device.
Entities
Related
Real-time stealth meeting copilot for Windows with local ASR and BYOK LLM
MeetingCopilot is a Windows application that provides real-time transcription of the other party in meetings or interviews, using either local FunASR or cloud ASR. It displays suggested answers on a first-person teleprompter that is invisible to screen sharing, powered by a bring-your-own-key (BYOK) LLM. It solves the problem of needing discreet, real-time assistance during remote meetings without being detected.
Notch: invisible voice-following teleprompter for meetings
Notch is a desktop overlay that displays notes invisibly during screen sharing and automatically scrolls to follow the user's speech using a local voice activity model. It helps professionals in meetings, interviews, or presentations stay on script without distracting others.
Vocert: tamper-proof audio recording with blockchain verification
Vocert is an iPhone/Apple Watch app that records audio and makes it tamper-evident using a hash chain and signed, timestamped receipts. It uses AI for transcription, key moment extraction, and legal analysis, and anyone can verify recordings in a browser without an account.
Tellie: Mac teleprompter that follows your voice word by word
Tellie is a Mac teleprompter app that tracks the actual words you say, highlighting your position and staying with you even if you skip ahead or improvise. It uses AI (Claude) for voice recognition and runs entirely on-device. Built by a non-programmer in 3 days, it solves the problem of rigid teleprompters for speakers who want natural delivery.
AI meeting tool for Arabic-English code-switching calls
Maglis is an AI meeting assistant that transcribes and summarizes calls where speakers switch between Arabic and English mid-sentence. It preserves dialect and code-switching, then generates minutes, action items, or proposals in the dominant language of the call. Built for professionals in the Middle East who need reliable multilingual meeting support.