Nexa AI GGUF Convertor
Request custom GGML quantized models via email
Voice conversion framework based on VITS
Generate and modify audio with models
Generate 3D scenes from one or two images
Interact with Aya Expanse to chat, speak, and generate images in 23 languages
Co-Speech Gesture Video Generation
Generate audio responses from uploaded or recorded audio
Generate MIDI music from prompts
High-fidelity Text-To-Speech
a super consistent video depth model
Generate images and answer questions using text input
Personalised Podcasts For All - Available in 13 Languages
Generate speech from text