Generate any application by Vibe Coding
Generate HTML templates using Jinja
Convert spoken words into text
Visualize embeddings in 3D space, powered by EmbeddingGemma
State-of-the-art TTS model under 25MB
Generate images from text prompts
Expressive Zeroshot TTS
Separate speakers in audio recordings
Generate an edited image based on text and input image
Ask questions and get informed answers
Generate 3D models from images
Generate audio from text with customizable voice and speed
(Unofficial) Gradio demo for Spark-TTS