Shypd.aiThe largest open index of AI toolsKimi-Audio is an open-source audio foundation model that excels in audio understanding, generation, and conversation. It provides an official implementation, models, and an evaluation toolkit for diverse audio processing tasks.
Trending
About
Kimi-Audio is an open-source audio foundation model designed to handle a wide variety of audio processing tasks within a single unified framework. It offers universal capabilities including automatic speech recognition (ASR), audio question answering (AQA), automatic audio captioning (AAC), speech emotion recognition (SER), sound event/scene classification (SEC/ASC), and end-to-end speech conversation. The model achieves state-of-the-art performance on numerous audio benchmarks, supported by large-scale pre-training on over 13 million hours of diverse audio and text data. Its novel architecture employs a hybrid audio input and an LLM core with parallel heads for efficient inference and low-latency audio generation. The repository includes code, model checkpoints, and a comprehensive evaluation toolkit to foster community research.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
