Hibiki Simple
High-Fidelity Simultaneous Speech-To-Speech Translation
Generate customized audio from text using a voice sample
DeepFake AI Tool for Videos & Images
Transcribe and translate audio files and YouTube videos
Generate images from text prompts for film-style visuals
A unified multimodal understanding and generation model.
Display a user interface for various tasks
Generate images using selected LoRAs and prompts
Voice assitant like jarvis
Import a portrait, click to move the head!