AI Video Analysis and Search

WhisperX is an automated speech recognition toolkit designed to convert spoken audio into text while maintaining precise synchronization with the original media. It functions as an integrated pipeline that combines transcription, phoneme-based alignment, and speaker diarization to produce structured, attributed transcripts. The project distinguishes itself through its use of forced alignment, which matches existing text to audio signals at the phoneme level to generate accurate word-level timestamps. It also incorporates speaker diarization to identify and label unique voices within a recording, allowing for the creation of transcripts that attribute specific segments to individual speakers. The system supports multilingual transcription and automated caption generation by sequencing multiple machine learning models, including transformer-based recognition and voice activity detection. These processes are optimized through GPU-accelerated tensor computation to handle large audio files and complex neural network operations.

Frigate is a self-hosted network video recorder that functions as a private, local AI-powered vision engine. It manages video streams by performing real-time object detection, tracking, and classification directly on local hardware, ensuring that security monitoring and activity recording remain independent of cloud services. The system distinguishes itself through a modular, hardware-accelerated video pipeline that offloads intensive decoding and machine learning inference to dedicated GPUs, NPUs, or specialized accelerators like Coral TPUs and Hailo modules. It utilizes state-based object tracking to maintain persistent identity and spatial coordinates for detected objects, enabling advanced behavioral analysis such as loitering detection and speed estimation. Users can further refine these capabilities through semantic search, which allows for text-to-image and image-to-image similarity queries across recorded footage. Beyond core detection, the platform provides comprehensive tools for spatial configuration, including declarative geometric masks and zone-based filtering to minimize false positives. It supports low-latency, peer-to-peer streaming for live viewing and integrates with smart home ecosystems to bridge camera feeds and event notifications. The system also includes specialized features for face recognition, license plate detection, and audio event analysis, all managed through a secure, token-authenticated API. The software is designed for containerized deployment, utilizing environment variables for configuration and standard protocols for certificate management and performance metric exposure.

This project is a self-hosted meeting transcription and summarization tool that converts audio recordings into text transcripts and structured notes using large language models. It functions as an enterprise meeting documentation manager, allowing for the organization and editing of timestamped records. The system prioritizes data privacy through local-first processing and the ability to deploy on private infrastructure. It supports a provider-agnostic architecture, enabling users to connect to local AI engines, self-hosted servers, or cloud-based API endpoints for both transcription and summarization. The platform covers a broad range of capabilities, including multilingual speech-to-text, real-time audio capture of system and microphone sounds, and hardware-accelerated transcription. It features a template-driven system for generating consistent summaries, role-based access control for team management, and tools for exporting content to PDF, Word, and Markdown formats. Security is handled through data-at-rest encryption and frameworks for regional data compliance such as GDPR and HIPAA.

Whisper is a high-performance speech-to-text inference engine that uses graphics hardware shaders to accelerate the transcription of spoken audio into written text. It implements a GPU-accelerated automatic speech recognition framework specifically designed to run Whisper models. The system focuses on high-speed processing for both recorded audio files and live microphone streams. It utilizes voice activity detection to analyze raw audio in real time, triggering the inference engine only when human speech is detected. The engine covers a broad range of capabilities including real-time audio capture, GPGPU inference optimization, and compute performance profiling to measure the execution time of individual shaders.

Heartlib is an audio processing library for large language models that provides tools for audio tokenization, compression, and cross-modal alignment. It implements core models for audio-text embedding, automatic speech recognition, neural codecs, and text-driven audio synthesis. The project features a text-to-audio synthesis engine capable of generating high-fidelity music and speech from text descriptions or reference files. It also includes a neural audio codec designed for low-bitrate compression that preserves acoustic structure and sound quality. Additional capabilities cover audio-text alignment via a shared latent space for retrieval, as well as transcription tools specifically designed to convert vocal lyrics and singing into written text.