Lugs

Simultaneously captures audio from system output (speakers/application audio) and microphone input using OS-level audio routing APIs, then routes both streams through a local or hybrid transcription engine. This dual-stream architecture enables comprehensive captioning of both incoming speech and computer-generated audio without requiring separate recording applications or manual audio mixing.

Processes audio streams through an on-device transcription model (likely Whisper or similar) that runs locally without sending audio to cloud servers, enabling sub-second latency for caption generation while maintaining privacy. The local architecture trades off some accuracy potential for immediate responsiveness and eliminates network dependency.

Renders real-time captions as a system-level overlay that persists across all applications and windows, using native OS graphics APIs (DirectX on Windows, Metal on macOS) to ensure captions remain visible regardless of active application. The overlay system includes positioning, styling, and transparency controls to minimize visual obstruction while maintaining readability.

Analyzes audio characteristics (pitch, timbre, speech patterns) to distinguish between different speakers in real-time, labeling transcript segments with speaker identifiers or names. The diarization engine uses voice embedding models to cluster similar voices and track speaker continuity across conversation segments, enabling multi-speaker transcripts without manual annotation.

Converts real-time transcription output into multiple standard formats (SRT, VTT, JSON, plain text) with configurable metadata (timestamps, speaker labels, confidence scores). The export pipeline includes options for transcript segmentation (by speaker, by time interval, by sentence) and can generate both human-readable and machine-parseable outputs for downstream processing.

Continuously analyzes incoming audio streams to detect signal-to-noise ratio (SNR), clipping, background noise patterns, and audio codec issues in real-time. The monitoring system provides visual/textual feedback on audio quality and can trigger automatic gain adjustment or noise suppression to maintain transcription accuracy, with configurable thresholds for different use cases.

Allows users to define custom keyboard shortcuts for common transcription operations (start/stop recording, pause/resume, export, toggle overlay visibility) with conflict detection against system and application hotkeys. The hotkey system uses OS-level keyboard hooks to capture shortcuts globally, even when the application window is not in focus, enabling hands-free control during active transcription.

Indexes completed transcripts using full-text search with support for speaker filtering, timestamp-based range queries, and confidence score thresholds. The search engine enables users to quickly locate specific phrases or speakers within large transcripts without manual scrolling, with results linked back to original timestamps for playback or export.

Detects the language of incoming audio automatically and switches transcription models in real-time to match detected language, supporting a curated set of languages (likely 10-20 based on local model constraints). The language detection uses audio feature analysis to identify language within the first few seconds of speech, enabling seamless transcription of multilingual conversations.

Provides a text editor interface for manual correction of transcription errors with word-level timestamp preservation and speaker label editing. The editor includes undo/redo functionality, batch find-and-replace for systematic corrections, and exports corrected transcripts while maintaining alignment with original audio timestamps for caption synchronization.