GLM OCR Demo
Multimodal OCR model for complex document understanding.
Multimodal OCR model for complex document understanding.
Convert spoken words into text
Vote on the latest Voice Clone TTS models!
Generate a Logo in 2 clicks
Convert spoken words into text
Chat with an AI-powered conversation model
Z-Anime 6B - CPU anime image generation via sd.cpp
Generate natural speech from text and custom cloned voices
Real-time speech transcription, entirely in your browser.
Generate responses with the GLM-5 language model
Real-time voice cloning entirely in your browser! (CPU)
Real-time voice cloning entirely in your browser! (CPU)
This space ''TeichAI/Nemotron-Cascade-14B-Thinking-C...''.
Space for LuxTTS: a 150x realtime voice cloning TTS model
Pocket TTS optimized for Hugging Face Spaces on CPU
Pocket TTS optimized for Hugging Face Spaces on CPU
Generate images from text prompts
Generate text using a pre-trained model
Generate text using a pre-trained model
Minimum working OpenAI Whisper pipeline