ModalityDance/AR-Omni
Generates text, images, and speech through a single decoder
View on index · View in 3D Map
Related repos
- Chatbot processes speech, vision, and text
- audio-driven avatar video generation with prompt-based control and full-body animation
- speech-to-text and text-to-speech with Llama-3, real-time chatbot
- Multimodal model with real-time speech synthesis
- Streaming speech-to-speech language model
- Transcribes and translates audio or images into text
- Generates images and text with unshared parameters
- Generates spatial audio from 360-degree video
- open-weight text-to-speech model for fast, natural voice synthesis
- Wearable for transcription and summaries
