Open Source Mac AI Text Generators
Sort By:
AI Text Generators for Mac
View 44 business solutionsBrowse free open source AI Text Generators and projects for Mac below. Use the toggles on the left to filter open source AI Text Generators by OS, license, language, programming language, and project status.
-
Go From Idea to Deployed AI App FastAccess Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.
-
$300 in Free Credit Across 150+ Cloud ServicesStart your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale with Google Cloud.
-
1
Text Generation Web UI
Oobabooga - The definitive Web UI for local AI, with powerful features
A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA. Dropdown menu for switching between models. Notebook mode that resembles OpenAI's playground. Chat mode for conversation and role playing. Instruct mode compatible with Alpaca and Open Assistant formats. Nice HTML output for GPT-4chan. Markdown output for GALACTICA, including LaTeX rendering. Custom chat characters. Advanced chat features (send images, get audio responses with TTS). Very efficient text streaming. Parameter presets, 8-bit mode. Layers splitting across GPU(s), CPU, and disk. CPU mode, FlexGen, DeepSpeed ZeRO-3, API with streaming and without streaming. LLaMA model, including 4-bit GPTQ. RWKV model, LoRA (loading and training), Softprompts, and extensions. -
2
KoboldCpp
Run GGUF models easily with a UI or API. One File. Zero Install.
KoboldCpp is an easy-to-use AI text-generation software for GGML and GGUF models, inspired by the original KoboldAI. It's a single self-contained distributable that builds off llama.cpp and adds many additional powerful features. -
3
gpt-j-api
API for the GPT-J language mode. Including a FastAPI backend
An API to interact with the GPT-J language model and variants! You can use and test the model in two different ways. These are the endpoints of the public API and require no authentication. Just SSH into a TPU VM. This code was tested on both the v2-8 and v3-8 variants. -
4
Intelligent Java
Integrate with the latest language models, image generation and speech
Intelligent java (IntelliJava) is the ultimate tool to integrate with the latest language models and deep learning frameworks using java. The library provides an intuitive functions for sending input to models like ChatGPT and DALL·E, and receiving generated text, speech or images. With just a few lines of code, you can easily access the power of cutting-edge AI models to enhance your projects. Access ChatGPT, GPT3 to generate text and DALL·E to generate images. OpenAI is preferred for quality results without tuning. Generate text; Cohere allows you to generate a language model to suit your specific needs. Generate audio from text; Access DeepMind’s speech models. The only dependencies is GSON. Required to add manually when using IntelliJava jar. However, if you imported this repo through Maven, it will handle the dependencies. -
99.99% Uptime for Your Most Critical DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
5
node-red-contrib-custom-chatgpt
Node-RED ChatGPT
A Node-RED node that interacts with OpenAI machine learning models like "ChatGPT". Install with the built-in Node-RED Palette manager. When editing the properties of the node, to get your OPENAI_API_KEY log in to ChatGPT. Create a new secret key" then copy and paste the "API key" into the node API_KEY property value. msg.payload should be a well-written prompt that provides enough information for the model to know what you want and how it should respond. Its success generally depends on the complexity of the task and quality of your prompt. A good rule of thumb is to think about how you would write a word problem for a middle schooler to solve. msg.payload should be a well-written prompt that provides enough information for the model to know what you want and how it should respond. -
6
gpt2-client
Easy-to-use TensorFlow Wrapper for GPT-2 117M, 345M, 774M, etc.
GPT-2 is a Natural Language Processing model developed by OpenAI for text generation. It is the successor to the GPT (Generative Pre-trained Transformer) model trained on 40GB of text from the internet. It features a Transformer model that was brought to light by the Attention Is All You Need paper in 2017. The model has 4 versions - 124M, 345M, 774M, and 1558M - that differ in terms of the amount of training data fed to it and the number of parameters they contain. Finally, gpt2-client is a wrapper around the original gpt-2 repository that features the same functionality but with more accessiblity, comprehensibility, and utilty. You can play around with all four GPT-2 models in less than five lines of code. Install client via pip. The generation options are highly flexible. You can mix and match based on what kind of text you need generated, be it multiple chunks or one at a time with prompts. -
7
CPT
CPT: A Pre-Trained Unbalanced Transformer
A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation. We replace the old BERT vocabulary with a larger one of size 51271 built from the training data, in which we 1) add missing 6800+ Chinese characters (most of them are traditional Chinese characters); 2) remove redundant tokens (e.g. Chinese character tokens with ## prefix); 3) add some English tokens to reduce OOV. Position Embeddings We extend the max_position_embeddings from 512 to 1024. We initialize the new version of models with the old version of checkpoints with vocabulary alignment. Token embeddings found in the old checkpoints are copied. And other newly added parameters are randomly initialized. We further train the new CPT & Chinese BART 50K steps with batch size 2048, max-seq-length 1024, peak learning rate 2e-5, and warmup ratio 0.1. Aiming to unify both NLU and NLG tasks, We propose a novel Chinese Pre-trained Un-balanced Transformer (CPT). -
8
AI Atelier
Based on the Disco Diffusion, version of the AI art creation software
Based on the Disco Diffusion, we have developed a Chinese & English version of the AI art creation software "AI Atelier". We offer both Text-To-Image models (Disco Diffusion and VQGAN+CLIP) and Text-To-Text (GPT-J-6B and GPT-NEOX-20B) as options. Making available complete source code of licensed works and modifications, which include larger works using a licensed work, under the same license. Copyright and license notices must be preserved. When a modified version is used to provide a service over a network, the complete source code of the modified version must be made available. Create 2D and 3D animations and not only still frames (from Disco Diffusion v5 and VQGAN Animations). Input audio and images for generation instead of just text. Simplify tool setup process on colab, and enable ‘one-click’ sharing of the generated link to other users. Experiment with the possibilities for multi-user access to the same link. -
9
AI Chatbots based on GPT Architecture
Training & Implementation of chatbots leveraging GPT-like architecture
Training & Implementation of chatbots leveraging GPT-like architecture with the aitextgen package to enable dynamic conversations. It sure seems like there are a lot of text-generation chatbots out there, but it's hard to find a python package or model that is easy to tune around a simple text file of message data. This repo is a simple attempt to help solve that problem. ai-msgbot covers the practical use case of building a chatbot that sounds like you (or some dataset/persona you choose) by training a text-generation model to generate conversation in a consistent structure. This structure is then leveraged to deploy a chatbot that is a "free-form" model that consistently replies like a human. Some of the trained models can be interacted with through the HuggingFace spaces and model inference APIs on the ETHZ Analytics Organization page on huggingface.co. -
Push Code. Get a Production URL. Done.Skip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
10
Accelerated Text
Accelerated Text is a no-code natural language generation platform
A picture is worth a thousand words. Or is it? Tables, charts, pictures are all useful in understanding our data but often we need a description – a story to tell us what are we looking at. Accelerated Text is a natural language generation tool which allows you to define data descriptions and then generates multiple versions of those descriptions varying in wording and structure. Accelerated Text is a no-code natural language generation platform. It will help you construct document plans which define how your data is converted to textual descriptions. With Accelerated Text you can use such data to generate text for your business reports, your e-commerce platform or your customer support system. Data descriptions require precision. Accelerated Text follows the principle of this strict adherence to data-bound text generation. Via its user interface, it provides instruments to define how the data should be translated into a descriptive text. -
11
Ad Generator
Professional text randomizer and ad generator by Airat Khalitov
Professional text randomizer and ad generator by Airat Khalitov / Professional text randomizer and ad generator. Author: Airat Halitov. Visit 'Plugins, Add New', click 'Upload Plugin', upload the file 'ad-generator.zip', and activate Ad Generator from your Plugins page. Add [ad_generator] shortcode to WordPress Page. Create a new WordPress Page, add [ad_generator] shortcode and save. Go to the page and use the ad generator. This is a program for industrial creation of pseudo-unique content. Used, for example, when registering a site in multiple directories. So that in each directory the site is described by text that is unique from the point of view of search engines. Unlike similar tools (synonymizers, dorgens), it allows you to maximize the readability of the resulting texts. -
12
Aida Lib
Aida is a language agnostic library for text generation
Aida is a language-agnostic library for text generation. When using Aida, first you compose a tree of operations on your text that includes conditions via branches and other control flow. Later, you fill the tree with data and render the text. A building block is a variable class: Var. Use it to represent a value that you want to control later. A variable can hold numbers (e.g. float, int) or strings. You can create branches and complex logic with Branch. The context, represented by the class Ctx, is useful to create rules that depends on what has been written before. Each object or literal that is passed to Aida is remembered by the context. Creating a reference expression is a common use-case, so we have a helper function called create_ref. You can compose operations on your text with some handy operators. -
13
BNFGen
Generates random text based on context-free grammars defined in BNF
BNFGen generates random text based on context-free grammar. You give it a file with your grammar, defined using BNF-like syntax, it gives you a string that follows that grammar. BNFGen is a CLI tool, an OCaml library. There are also official JS bindings available via NPM. Project goals are to make it easy to write and share grammar and give the user total control of and insight into the generation process. BNFGen provides a "DSL" for grammar definitions. It's a familiar BNF-like syntax with a few additions. One problem with using straight BNF for driving language generators is that you have no control over the process. BNFGen adds two features to fix that. The canonical way to express repetition in BNF is to use a self-referential recursive rule. In classic BNF, that can easily lead to the process terminating to early, since there's a 50% chance that it will take the non-recursive alternative. -
14
Basaran
Basaran, an open-source alternative to the OpenAI text completion API
Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models. The open source community will eventually witness the Stable Diffusion moment for large language models (LLMs), and Basaran allows you to replace OpenAI's service with the latest open-source model to power your application without modifying a single line of code. Stream generation using various decoding strategies. Support both decoder-only and encoder-decoder models. Detokenizer that handles surrogates and whitespace. Multi-GPU support with optional 8-bit quantization. Real-time partial progress using server-sent events. Compatible with OpenAI API and client libraries. Comes with a fancy web-based playground. Docker images are available on Docker Hub and GitHub Packages. -
15
BlogWizard
Generate blog articles from video or audio
BlogWizard is a demo/utility project built on top of Groq’s LLM infrastructure that converts video or audio content into well-structured blog posts, enabling creators to repurpose multimedia content into text — useful for SEO, accessibility, or reaching audiences that prefer reading. The tool uses transcription (e.g. via Whisper) to extract text from audio/video, then runs an LLM-based generation pipeline to transform that content into coherent, readable blog-format posts — with sections, formatting, and possibly metadata. This bridges the gap between modern multimedia content (podcasts, YouTube videos, interviews) and traditional written content, making cross-format publishing more efficient. For content creators, educators, or businesses producing audio/video content, blogwizard automates the tedious, manual process of transcription + blog writing, saving time while ensuring output quality. -
16
CRSLab
CRSLab is an open-source toolkit
CRSLab is an open-source toolkit for building Conversational Recommender System (CRS). It is developed based on Python and PyTorch. CRSLab has the following highlights. Comprehensive benchmark models and datasets: We have integrated commonly-used 6 datasets and 18 models, including graph neural network and pre-training models such as R-GCN, BERT and GPT-2. We have preprocessed these datasets to support these models, and release for downloading. Extensive and standard evaluation protocols: We support a series of widely-adopted evaluation protocols for testing and comparing different CRS. General and extensible structure: We design a general and extensible structure to unify various conversational recommendation datasets and models, in which we integrate various built-in interfaces and functions for quickly development. Easy to get started: We provide simple yet flexible configuration for new researchers to quickly start in our library. Human-machine interaction interfaces. -
17
Dickinson
Text generation language
Dickinson is a text-generation language. You can try out the language on the web without installing anything. Binaries for some platforms are available on the releases page. There is an install script that will try to download the right release for your computer. -
18
GPT-2 FR
GPT-2 French demo | Démo française de GPT-2
OpenAI GPT-2 model trained on four different datasets in French. Books in French, French film scripts, reports of parliamentary debates, Tweet by Emmanuel Macron, allowing to generate text. Tensorflow and gpt-2-simple are required in order to fine-tune GPT-2. Create an environment then install the two packages pip install tensorflow==1.14 gpt-2-simple. A script and a notebook are available in the src folder to fine-tune GPT-2 on your own datasets. The output of each workout, i.e. the folder checkpoint/run1, is to be put ingpt2-model/model1 model2 model3 etc. You can run the script deploy_cloudrun.shto deploy all your different models (into gpt2-model) at once. However, you must have already initialized the gcloud CLI tool (Cloud SDK). -
19
GPT2 for Multiple Languages
GPT2 for Multiple Languages, including pretrained models
With just 2 clicks (not including Colab auth process), the 1.5B pretrained Chinese model demo is ready to go. The contents in this repository are for academic research purpose, and we do not provide any conclusive remarks. Research supported with Cloud TPUs from Google's TensorFlow Research Cloud (TFRC) Simplifed GPT2 train scripts（based on Grover, supporting TPUs). Ported bert tokenizer, multilingual corpus compatible. 1.5B GPT2 pretrained Chinese model (~15G corpus, 10w steps). Batteries-included Colab demo. 1.5B GPT2 pretrained Chinese model (~30G corpus, 22w steps). -
20
Insert Text
Extends the media pool with an effect for outputting text in the image
This addon expands the media manager with the effect Bild. The effect can be used, for example, to display a copyright notice, creation date, image title, etc. on images. The values set for the effect are considered "default" and can be changed individually for each image if necessary via the effect parameters in meta data. The text source of the effect can be selected here. inputfor the field Textausgabe or any meta field from the media pool. A text area can also be selected from the media pool, which opens up even more possibilities for this effect. The values set in the effect are considered "default" for all images to which this media type is applied. If a "text area" from the meta data has been selected as the text source, an individual setting for the effect can be applied to each image. -
21
LegacyInsight
Legacy reverse engineering tool
LegacyInsight is an AI-powered reverse engineering platform that transforms legacy software systems into comprehensible business logic. Using cutting-edge GenAI, it analyzes legacy and extracts core operations, business rules, and data transformations—all translated into natural language. LegacyInsight supports enterprise-grade systems built on Java, COBOL, NET and other legacy stacks, helping organizations reclaim understanding of business-critical code. -
22
Market Reporter
Automatic Generation of Brief Summaries of Time-Series Data
Market Reporter automatically generates short comments that describe time series data of stock prices, FX rates, etc. This is an implementation of Murakami et al. This tool stores data to Amazon S3. Ask the manager to give you AmazonS3FullAccess and issue a credential file. For details, please read AWS Identity and Access Management. Install Docker and Docker Compose. Edit envs/docker-compose.yaml according to your environment. Then, launch containers by docker-compose. We recommend to use pipenv to make a Python environment for this project. Suppose you have a database named master on your local machine. Prediction submodule generates a single comment of a financial instrument at specified time by loading a trained model. -
23
Minimal text diffusion
A minimal implementation of diffusion models for text generation
A minimal implementation of diffusion models of text: learns a diffusion model of a given text corpus, allowing to generate text samples from the learned model. The main idea was to retain just enough code to allow training a simple diffusion model and generating samples, remove image-related terms, and make it easier to use. To train a model, run scripts/train.sh. By default, this will train a model on the simple corpus. However, you can change this to any text file using the --train_data argument. Note that you may have to increase the sequence length (--seq_len) if your corpus is longer than the simple corpus. The other default arguments are set to match the best setting I found for the simple corpus. -
24
Node.js Client For NLP Cloud
NLP Cloud serves high performance pre-trained or custom models
This is the Node.js client (with Typescript types) for the NLP Cloud API. NLP Cloud serves high-performance pre-trained or custom models for NER, sentiment analysis, classification, summarization, dialogue summarization, paraphrasing, intent classification, product description and ad generation, chatbot, grammar and spelling correction, keywords and keyphrases extraction, text generation, image generation, blog post generation, text generation, question answering, automatic speech recognition, machine translation, language detection, semantic search, semantic similarity, tokenization, POS tagging, embeddings, and dependency parsing. It is ready for production, and served through a REST API. You can either use the NLP Cloud pre-trained models, fine-tune your own models, or deploy your own models. -
25
PHP Client For NLP Cloud
NLP Cloud serves high performance pre-trained or custom models for NER
NLP Cloud serves high performance pre-trained or custom models for NER, sentiment-analysis, classification, summarization, dialogue summarization, paraphrasing, intent classification, product description and ad generation, chatbot, grammar and spelling correction, keywords and keyphrases extraction, text generation, image generation, blog post generation, code generation, question answering, automatic speech recognition, machine translation, language detection, semantic search, semantic similarity, tokenization, POS tagging, embeddings, and dependency parsing. It is ready for production, served through a REST API. You can either use the NLP Cloud pre-trained models, fine-tune your own models, or deploy your own models. Pass the model you want to use and the NLP Cloud token to the client during initialization. If you are making asynchronous requests, you will always receive a quick response containing a URL.
