Search Results for "text generation"
Sort By:
Showing 46 open source projects for "text generation"
View related business solutions-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
1
Concat
Open-Source CapCut replacement (MCP supported)
Concat is a free and open-source desktop video editor positioned as a local alternative to subscription-based editors such as CapCut. It uses a native Rust engine and performs editing entirely on the user’s machine. Projects can contain multiple tracks and timelines for more complex compositions. Core editing tools include splitting, trimming, merging, transitions, and playback-speed adjustment. Offline features include automatic captions, local text-to-speech voices, voice processing,... -
2
Mermaid
Diagram and flowchart generation from text similar to markdown
Mermaid is a JavaScript-based diagram and flowchart generating tool that uses markdown-inspired text for fast and easy generation of diagrams and charts. Forget about using heavy tools to explain your code. Mermaid greatly simplifies documentation with its simple markdown-like script language, and offers a great range of diagram and chart options. The latest version of Mermaid comes with a number of bug fixes and enhancements, as well as a new diagram type, entity relationship diagrams. ... -
3
UniMate
UniMate: One Unified Model to Animate Diverse Skeletons
...It is designed to handle bipeds, quadrupeds, birds, marine creatures, insects, serpentine rigs, and articulated rigid objects with one unified model. Its topology-aware diffusion transformer conditions generation on skeleton structure rather than requiring a fixed character template. The accompanying UniML3D dataset contains 13,006 text-paired motion sequences with unified skeletal canonicalization. Inference can generate motion for unseen skeleton topologies without per-skeleton retraining or test-time optimization. The same model supports text-guided motion editing, in-betweening, and longer motion expansion. ... -
4
Podcastfy.ai
Transforming Multimodal Content into Captivating Multilingual Audio
Podcastfy is an open-source Python package that transforms multi-modal content (text, images) into engaging, multi-lingual audio conversations using GenAI. Input content includes websites, PDFs, youtube videos as well as images. Unlike UI-based tools focused primarily on note-taking or research synthesis (e.g. NotebookLM), Podcastfy focuses on the programmatic and bespoke generation of engaging, conversational transcripts and audio from a multitude of multi-modal sources enabling customization and scale. -
Paessler: Easy to Use With Enterprise Power. Free TrialYou shouldn't have to choose between a monitoring tool that's easy to use and one that's powerful enough for a complex environment. PRTG's low-code interface lets any admin build dashboards, set alerts and monitor devices without scripting, while custom sensors and full API access are there when your team needs deeper control. One platform, no compromise. Download a free 30-day trial now.
-
5
Speakr
Speakr is a personal, self-hosted web application
Speakr is an open-source, real-time text-to-speech (TTS) web application that allows users to convert written text into natural-sounding speech in just a few clicks. It provides a clean, user-friendly interface where users can input text, choose a voice style or language, and immediately hear the output, making it ideal for accessibility, content creation, and learning applications. -
6
IOPaint
Image inpainting tool powered by SOTA AI Model
...Designed to be fully self-hosted and flexible, IOPaint supports a variety of underlying generators and inpaint models — from LaMa erase networks to Stable Diffusion-based replace/object generation — giving users multiple ways to refine or reconstruct images by removing unwanted elements or expanding artwork beyond its original boundaries. Its feature set includes erasing people, watermarks, or defects, adding or replacing objects, applying text-aware edits, and extending images outward (outpainting) to fill contours or expand compositions. -
7
PersonaPlex
PersonaPlex code
...PersonaPlex also supports persona and voice control, allowing developers to define the role and speaking style of the agent using text prompts and voice conditioning, making it suitable for applications like customized voice assistants, interactive character agents, or domain-specific conversational tools. Internally, it processes continuous audio streams in a hybrid input format so that speech understanding and generation occur jointly. -
8
Flameshot
Powerful yet simple to use screenshot software 🖥️ 📸
Flameshot is a powerful yet simple-to-use open-source screenshot software designed for efficiency and flexibility. It is a free and open-source, cross-platform tool that helps users capture screenshots with ease. Licensed under GPL v3, Flameshot provides a wide range of built-in features that save time during screen capturing and editing. The software offers a clean, straightforward interface that makes taking and annotating screenshots quick and intuitive. Users can customize the... -
9
Materializr
Open-source parametric 3D CAD for makers
Materializr is a free, open-source parametric 3D CAD application designed for makers, hobbyists, and technical designers. It provides an accessible interface for creating precise solid models without requiring complex professional CAD software. Users can draw dimensioned sketches with geometric constraints and transform them into three-dimensional objects. Its OpenCASCADE geometry engine supports extrusion, lofting, fillets, chamfers, and Boolean operations. The software includes tools for... -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
10
oh-my-ppt
Describe what you need — a presentation, lesson, or story
Oh My PPT is a free, open-source, local-first AI presentation creator that generates editable HTML slides from natural language instructions. Users can describe a topic, upload supporting documents, or import existing PowerPoint presentations to create new slide decks. Its AI tools generate outlines, layouts, illustrations, and speaker notes using configurable language and image models. A visual editor allows users to move, resize, duplicate, and modify individual slide elements. More than... -
11
FreeShow
FreeShow is a free and open-source, user-friendly presenter software
FreeShow is a free, open-source presentation application designed for churches, events, and live productions. It allows users to create and display slideshows containing song lyrics, scripture passages, images, videos, and other presentation content. The software provides a customizable editor for adjusting text formatting, visual styles, backgrounds, and slide layouts. Users can organize presentations into shows and control content during live events. It supports multiple simultaneous... -
12
Capptivo
Give your demos the spotlight they deserve ( Mac/Windows/Linux )
Capptivo is a free, open-source screen recording and editing application designed for creating professional software demonstrations and tutorials. It captures desktop screens, application windows, or selected areas with optional webcam and microphone recording. Users can add annotations, highlight interactions, and control recording sessions through keyboard shortcuts. Its timeline editor provides automatic and manual zoom effects that follow cursor movements or emphasize selected regions.... -
13
OpenChatCut
Open-source, local-first conversational AI video editor
...Its multitrack timeline supports trimming, transitions, effects, keyframes, and audio mixing. Transcript-based editing allows users to modify footage through spoken text and generate synchronized captions. The software includes motion graphics, color grading, and AI-assisted media generation. Codex, Claude Code, and other agents can interact with projects through MCP integration. Edits remain reversible and fully adjustable rather than becoming fixed outputs. Projects and media are stored locally by default, with exports supporting MP4, audio, captions, and FCPXML. -
14
Subtitle Translator
Translate subtitle using LLM
Subtitle Translator is an open-source desktop application that uses large language models, including ChatGPT, to translate subtitles into multiple languages. It considers preceding and following dialogue to produce context-aware translations that preserve conversational meaning. The application supports SRT, ASS, SSA, and WebVTT subtitle formats. Its Strict mode maintains a one-to-one correspondence between original and translated subtitle cues. Adaptive mode can merge or split adjacent cues... -
15
Ink/Stitch
Ink/Stitch: an Inkscape extension for machine embroidery design
Ink/Stitch is a free, open-source machine embroidery design extension for Inkscape. It transforms vector graphics into stitch patterns compatible with embroidery machines. Users can create detailed designs using running stitches, satin stitches, fill patterns, and manual stitch placement. The software provides customizable stitch parameters, underlays, and routing tools for optimizing embroidery results. Its lettering system includes pre-digitized fonts and support for custom embroidery... -
16
Moshi
A speech-text foundation model for real time dialogue
...At inference, the stream from the user is taken from the audio input, and the one for Moshi is sampled from the model's output. Along these two audio streams, Moshi predicts text tokens corresponding to its own speech, its inner monologue, which greatly improves the quality of its generation. A small Depth Transformer models inter codebook dependencies for a given time step, while a large, 7B parameter Temporal Transformer models the temporal dependencies. -
17
AnimateDiff
Plug-n-play module turning text-to-image models into animation
AnimateDiff is an open-source project designed to enhance text-to-image diffusion models by adding animation capabilities. It allows users to turn static images generated by popular text-to-image models into animated sequences without requiring additional model training. This plug-and-play tool is compatible with a wide range of community models and facilitates the generation of animation directly from pre-existing text-to-image models. -
18
jPicEdt
Another drawing editor for LaTeX with PSTricks & TikZ
jPicEdt is an extensible internationalized vector-based drawing editor for LaTeX and related packages (TikZ, PsTricks,...), written in Java. It is also a library of reusable high-level graphic primitives. -
19
htmid
Generative Music For Beginners and Everyone Else
Generative music is a fascinating and innovative approach to music creation that involves creating procedurally generated music that evolves and changes over time. Whether you're a beginner or a seasoned musician, this guide will introduce you to the world of generative music and show you how to create your own live music performances. Generative music is music that is ever-changing and created in real-time. It can be created by anyone, with or without musical experience. Learn how to... -
20
A collection of graphical midi based editors, each made specifically for the Boss SY-1000 , Roland VG-99 guitar, or VB-99 bass synth units, which provide an alternative to the Boss/Roland version of midi editors, with full features and control of the SY-1000, VG-99, or VB-99 from a Windows, Mac, or Linux computer.
-
21
Obsidian MEDILIG
Obsidian MEDILIG (Medical Life Guard) App Local-First Offline-First
Obsidian MEDILIG (Medical Life Guard): An easy-to-use, flexible, secure, cross-platform medical knowledge management system for patient's Electronic Health Record (EHR) that is built on top of Obsidian software application for the design, implementation and use of autonomous, multilingual, clinical documents from primary care to continuing care. -
22
Gen-PixAi
modelAI 100% work Pixel Drawing Free No Limited
...NPCs, monsters, equipment, item drops, and skill effects. Commercial and non-commercial projects with clear licensing rules. ✨ Key Features ✅ AI Pixel Generator: text → sprite/tileset (sizes 16×16, 24×24, 32×32, 48×48, 64×64, custom). ✅ Style Controls: NES/GB/SNES/GENESIS-like palettes, dithering, automatic outlines, tileability. ✅ Batch & Seed: batch generation + seed for reproducibility. -
23
LPub3D
LDraw™ editor for LEGO® style digital building instructions.
LPub3D is an Open Source WYSIWYG editing application for creating LEGO® style digital building instructions. LPub3D is developed and maintained by Trevor SANDY. It uses the LDraw™ parts library, the most comprehensive library of digital Open Source LEGO® bricks available (www.ldraw.org/ ) and reads the LDraw LDR and MPD model file formats. LPub3D is available for free under the GNU Public License v3 and runs on Windows, Linux and macOS Operating Systems. LPub3D is also... -
24
Image16
Image viewer/editor specialized in astrophotography 16bits processing
Opens/saves TIF, FITS, PNG, XISF, PXM, RAW, JPG, XCF, PSD, WEBP. AsinH, Sqrt, Ln, Exp and Sqr stretching, HSL and RGB adjusting, Levels and Curves adjusting and Background Extraction for Color Balance, Flatness and Gradient Correction. Arithmetic between images. Resizing and croping. Color Balance based on background, selection or stars B-V (after platesolving). Debayering/Bayering. Inversion, mirroring, rotation, barrel/pincushion correction. RGB alignment/shifting. Erode, Dilate, ...... -
25
AudioCraft
Audiocraft is a library for audio processing and generation
AudioCraft is a PyTorch library for text-to-audio and text-to-music generation, packaging research models and tooling for training and inference. It includes MusicGen for music generation conditioned on text (and optionally melody) and AudioGen for text-conditioned sound effects and environmental audio. Both models operate over discrete audio tokens produced by a neural codec (EnCodec), which acts like a tokenizer for waveforms and enables efficient sequence modeling. ...
