Directory
Published directory entries matching your search.
KanjiTomo is an OCR program for identifying Japanese text from images, optimized for kanji recognition. Pointing the mouse at any image on screen performs kanji and dictionary lookup at the same time, and both horizontal and vertical text are supported. Java is required, and it has been tested on Windows 10.
LlamaIndex is a platform focused on AI agents for document optical character recognition (OCR) and workflow automation. Its LlamaParse tool is designed to process complex documents including those with tables, charts and images, and can perform parsing, extraction, splitting, classification and indexing of document content.
MuseGen is an AI music generation studio that turns text prompts into songs. It composes melodies, lyrics and vocals, offers multi-genre styles, and allows editing and export in MP3, WAV or MIDI. It also separates tracks into stems and can turn songs into MIDI or music videos. A paid subscription gives monthly credits for generating videos, images and songs.
Pictriev is a face search engine that finds look-alike celebrities on the web using face recognition. It accepts a photo of a frontal face, preferably with the gap between the eyes more than 80 pixels wide. Results vary with photo resolution or quality, and only jpg files under 200K bytes are accepted.
Resemble AI provides multimodal deepfake detection and watermarking for enterprise. It powers real-time detection of synthetic audio, video, and images, offers APIs, intelligence insights, and identity registration. It includes tools like meetings protection, agent detection, a Chrome extension, and integrates with Microsoft Teams. The company develops research models such as DETECT-World and PerTh Multimodal. It serves industries including telecom, finance, media, health, and public sector.
Structifi is an AI-powered tool designed for optical character recognition (OCR) and structured data extraction. It converts content from files including PDFs and images into actionable structured data, supporting use cases such as extracting sales leads, contacts, exam papers, and catalog information. The tool can also convert files to text, Excel, and other structured data formats.
Whisper command line client compatible with the original OpenAI client and based on CTranslate2. It uses CTranslate2 and the Faster-whisper implementation. The project lists Docker images with pre-loaded models, speaker diarization, voice activity detection and live transcription from a microphone. It is installed as a Python package or run from a Docker image.
