MoonshotAI/Kimi-Audio
Trained on 13M hours of mixed audio and text data
View on index · View in 3D Map
Related repos
- Mixture-of-Experts vision-language model
- Trains speech recognition models for twelve dollars
- Muon optimizer for training large language models
- Multimodal model with agentic capabilities
- speech recognition, synthesis, and audio tools for many platforms
- Text-to-audio model that generates speech and sounds from text
- Transcribes and summarizes audio with Cloudflare AI Workers
- Text-to-speech engine for long-form audio
- Generates playlists through sonic analysis of local audio files
