Github Projects

Qwen3-TTS

Clone any voice in 3 seconds and generate natural speech in multiple languages (10 languages). You can control tone, speed, and emotion via text instructions. A family of open-source models with a streaming latency of approximately 97 ms

Clone any voice in 3 seconds and generate natural speech in multiple languages (10 languages). You can control tone, speed, and emotion via text instructions. A family of open-source models with a streaming latency of approximately 97 ms » Learn more: ChatGPT Perplexity Free 35553 Useful Links Official Website Hugging Face GitHub

Gemma 3n

A lightweight multimodal AI model, capable of processing text, image, audio and video on all your devices, even mobile ones. Fast execution, efficient resource management and support for over 140 languages (open-source project).

A lightweight multimodal AI model, capable of processing text, image, audio and video on all your devices, even mobile ones. Fast execution, efficient resource management and support for over 140 languages (open-source project). » Learn more: ChatGPT Perplexity Verified Tool Free 23443 Useful Links Official Website Documentation Models AIStudio Demo

Hunyuan-A13B

An open source language model optimized for advanced reasoning, understanding of long contexts (256K tokens) and efficiency on limited resources. Ideal for search, agentic and multilingual processing

An open source language model optimized for advanced reasoning, understanding of long contexts (256K tokens) and efficiency on limited resources. Ideal for search, agentic and multilingual processing » Learn more: ChatGPT Perplexity Free 22243 Useful Links Official Website Hugging Face GitHub API

Chatterbox Turbo

Recreate a voice from 5 seconds of audio and produce real-time speech synthesis (open source TTS model licensed under MIT). Integrated PerTh watermark for verification, suitable for chatbots, customer support, and avatars

Recreate a voice from 5 seconds of audio and produce real-time speech synthesis (open source TTS model licensed under MIT). Integrated PerTh watermark for verification, suitable for chatbots, customer support, and avatars » Learn more: ChatGPT Perplexity Free 21061 Useful Links Official Website Hugging Face GitHub

GLM-Image

An open-source AI image generator with 16 billion parameters that excels at displaying text. This model also supports image editing, style transfer, identity preservation, and multi-subject consistency

An open-source AI image generator with 16 billion parameters that excels at displaying text. This model also supports image editing, style transfer, identity preservation, and multi-subject consistency » Learn more: ChatGPT Perplexity Free 19194 Useful Links Official Website Hugging Face GitHub Guide

OmniGen

An open-source AI tool for generating images from text. Create new illustrations by combining different styles or models to obtain optimized results

An open-source AI tool for generating images from text. Create new illustrations by combining different styles or models to obtain optimized results » Learn more: ChatGPT Perplexity Free 16281 Useful Links Official Website Hugging Face GitHub

StoryDiffusion

local · open source

An AI tool that generates coherent images and videos over long sequences thanks to an auto-attention mechanism. Create compelling stories while maintaining character and plot consistency

An AI tool that generates coherent images and videos over long sequences thanks to an auto-attention mechanism. Create compelling stories while maintaining character and plot consistency » Learn more: ChatGPT Perplexity Free 14235 Useful Links Official Website Hugging Face GitHub Replicate

TransPixar Adobe

adobe · lora

A video generator that adds transparent effects such as smoke or reflections. Integrate visual elements naturally into your scenes to create smooth transitions and realistic special effects (VFX)

A video generator that adds transparent effects such as smoke or reflections. Integrate visual elements naturally into your scenes to create smooth transitions and realistic special effects (VFX) » Learn more: ChatGPT Perplexity Free 12853 Useful Links Official Website Hugging Face GitHub arXiv Paper

Suno AI Bark

A free and open-source text-to-speech to easily generate realistic and natural voices

A free and open-source text-to-speech to easily generate realistic and natural voices » Learn more: ChatGPT Perplexity Free 10930 Similar AI Tools ElevenLabs Uberduck FreeTTS

YuE2

Github Projects · Github Projects

An open-source music generator that turns your lyrics into a complete song. This AI creates an editable score and then generates a complete song with vocals and instrumental accompaniment

An open-source music generator that turns your lyrics into a complete song. This AI creates an editable score and then generates a complete song with vocals and instrumental accompaniment

Google MedASR

Easily transcribe medical dictations and exchanges between doctors and patients. The system is based on a voice recognition model with 105 million parameters, trained on 5,000 hours of medical data covering radiology and internal medicine

Easily transcribe medical dictations and exchanges between doctors and patients. The system is based on a voice recognition model with 105 million parameters, trained on 5,000 hours of medical data covering radiology and internal medicine » Learn more: ChatGPT Perplexity Verified Tool Free 7463 Useful Links Official Website Hugging Face GitHub Quick Access

MagicAnimate

Github Projects · Github Projects

Animate a person or a fictional character from a simple image. This video project is available on GitHub and is already up and working

Animate a person or a fictional character from a simple image. This video project is available on GitHub and is already up and working

MaleCNS Connectome

The first complete map of the brain and nervous system of a male fruit fly, featuring more than 166,000 neurons and 125 million connections, freely explorable online

The first complete map of the brain and nervous system of a male fruit fly, featuring more than 166,000 neurons and 125 million connections, freely explorable online » Learn more: ChatGPT Perplexity Verified Tool Free 5679 Useful Links Official Website GitHub Neural Mapping Dataset

Screenshot To Code

Github Projects · Github Projects

An ambitious GitHub project that can analyse a screenshot and give you the code to achieve the same result

An ambitious GitHub project that can analyse a screenshot and give you the code to achieve the same result

StyleCLIP

Github Projects · Github Projects

Manipulate your images with ease using a text-based AI prompt. An AI that simultaneously uses StyleGAN and CLIP

Manipulate your images with ease using a text-based AI prompt. An AI that simultaneously uses StyleGAN and CLIP

StableLM

Github Projects · Github Projects

An AI that could become a free and open source alternative to ChatGPT

An AI that could become a free and open source alternative to ChatGPT

DragGAN

Github Projects · Github Projects

A new AI expert in image manipulation and transformation (live). Beta version available

A new AI expert in image manipulation and transformation (live). Beta version available

ThinkSound

Github Projects · Github Projects

Generate and edit soundtracks for your videos using a step-by-step AI model. Set consistent moods, adjust sound effects and perfectly synchronize audio and visuals

Generate and edit soundtracks for your videos using a step-by-step AI model. Set consistent moods, adjust sound effects and perfectly synchronize audio and visuals

LivePortrait AI

Github Projects · Github Projects

Animate portraits with a single image. This AI lets you quickly obtain realistic results via precise settings and a wide variety of styles

Animate portraits with a single image. This AI lets you quickly obtain realistic results via precise settings and a wide variety of styles

KV-Edit

Github Projects · Github Projects

A revolutionary approach to image editing that perfectly preserves the background during modifications. Edit specific areas precisely while maintaining perfect visual consistency

A revolutionary approach to image editing that perfectly preserves the background during modifications. Edit specific areas precisely while maintaining perfect visual consistency

Open Lovable

Github Projects · Github Projects

A high-quality open-source AI tool for cloning websites and generating complete React applications in seconds

A high-quality open-source AI tool for cloning websites and generating complete React applications in seconds

MidJourney Styles

A prompts generator for Midjourney containing styles, keywords, resolution comparison, image weight, etc.

A prompts generator for Midjourney containing styles, keywords, resolution comparison, image weight, etc. » Learn more: ChatGPT Perplexity Free 3534 Similar AI Tools Lexica.art Openart AI Prompt Optimizer

Kokoro-82M TTS

Github Projects · Github Projects

An ultra-fast, open-source text-to-speech model that transforms your texts into natural speech (82M parameters only). Create British or American English voices in 10 different styles

An ultra-fast, open-source text-to-speech model that transforms your texts into natural speech (82M parameters only). Create British or American English voices in 10 different styles

Parler-TTS

Github Projects · Github Projects

An open-source AI tool that generates natural voices from text using a model with 600 million parameters. Create your own voice

An open-source AI tool that generates natural voices from text using a model with 600 million parameters. Create your own voice