Github Projects AI Tools

TransPixar Adobe is a video generator that adds transparent effects such as smoke or reflections. Integrate visual elements naturally into your scenes (VFX).

Easily transcribe medical dictations and doctor-patient conversations with Google's MedASR. The system is based on a speech recognition model.

Recreate a voice from 5 seconds of audio and produce real-time speech synthesis with Chatterbox Turbo (an open source model).

GLM-Image (Z.ai) is a free and open-source AI image generator that excels at displaying text. This model also supports image editing, style transfer, identity preservation, and multi-subject consistency.

Open Lovable: Clone websites in React in seconds using AI. Create modern, open-source, and free applications with Firecrawl.

Generate high-quality musical compositions via InspireMusic, an open-source AI model trained on over 100,000 songs. Create songs for free.

Hunyuan-A13B is an open source language model with MoE architecture (80B parameters, 13B active) optimized for advanced reasoning, ultra-long contexts (256K tokens) and agent tasks.

Discover Gemma 3n (Google DeepMind), a lightweight multimodal AI model capable of processing text, image, audio and video on all your devices, even mobile ones.

TTT-MLP is a powerful template that generates one-minute videos with exceptional temporal coherence. Transform simple text storyboards into fluid animations.

KV-Edit is a new image-editing system that perfectly preserves the background when you edit. Maintain perfect visual consistency.

Control the movements of your AI-generated videos with Go-with-the-Flow. Transfer animations between scenes, add camera effects and more.

Kokoro-82M TTS is an ultra-fast, open-source text-to-speech model that transforms your texts into natural speech (82M parameters only).

Generate HD images seven times faster with Switti. Benefit from an architecture that optimizes memory and visual quality.

ThinkSound by FunAudioLLM: Generate & edit hyper-realistic video sound with Chain-of-Thought AI. Create immersive soundscapes, refine audio by text.