AI models directory for capability-aware discovery

SparkDesk is a family of large language models developed by iFLYTEK, designed to integrate with the company's voice recognition and industry-specific solutions. The models are optimized for Chinese language understanding and generation, with capabilities spanning text, code, and multimodal tasks. They are deployed via cloud APIs and on-premises solutions, with a focus on enterprise applications in education, healthcare, and smart devices.

Whisper Large v3 is a state-of-the-art open-source speech-to-text model developed by OpenAI, designed for robust multilingual transcription and translation. It excels in production audio workflows, offering high accuracy across diverse languages and acoustic conditions. The model is self-hostable, customizable, and widely used in voice applications, meeting accessibility, and batch processing pipelines.

CLAP HTSAT-Fused is a contrastive language-audio pretraining model that learns a shared embedding space between audio and natural language descriptions. It uses HTSAT as the audio encoder and RoBERTa as the text encoder, with a feature fusion mechanism, trained on LAION-Audio-630K. It supports zero-shot audio classification, retrieval, and feature extraction.

MiniMax ABAB is a family of large language models developed by MiniMax, a Chinese AI startup. The models are designed for chat, voice, and multimodal applications, offering API access for developers. The flagship model, ABAB, is a dense transformer model with 1.8 trillion parameters, trained on a large corpus of text and code. It supports long context windows (up to 256k tokens) and is optimized for reasoning, instruction following, and multilingual tasks. The model is available via API and has been integrated into various applications, including conversational AI and content generation.

Kokoro-82M is an open-weight text-to-speech model with 82 million parameters, fine-tuned from StyleTTS2-LJSpeech. It supports English and Arabic, delivers quality comparable to larger models, and is released under Apache 2.0. With over 16.7 million downloads, it is designed for efficient deployment in production and personal projects.