Mirei
🪷
39
A cutting-edge speech generation model with stereo support
A cutting-edge speech generation model with stereo support
Generate speech with voice cloning, now in four languages!
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
Generate speech from text via voice design, cloning, or presets
Free platform to access multiple AI models
Chat with a local LLaMA language model
Chat with text or text+image (using Mistral Small)
Generate AI text responses with Qwen2.5‑7B model
Chat with AI that understands text and images
High-fidelity 3D Generation from images
generate a video from an image with a text prompt
Demo of the Collection of Qwen Image Edit LoRAs