Search Results for "caption"
Sort By:
Showing 79 open source projects for "caption"
View related business solutions-
$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.
-
Demo Series - Small Business Backup By VeeamWatch this on-demand demo series and learn how to protect your Microsoft 365 data with clear, simple, actionable steps that are easy to implement for businesses of all sizes.
-
1
Caption Studio Pro
Fast, offline video captioning tool optimized for entry-level GPUs.
Caption Studio Pro is a lightweight desktop application designed for generating video subtitles 100% offline. Powered by the Faster-Whisper engine, it focus on providing accurate transcriptions while maintaining maximum data privacy by processing everything locally on your machine. A key highlight of this tool is its focus on accessibility for entry-level hardware. -
2
abogen
Generate audiobooks from EPUBs, PDFs and text with captions
...This can be very useful for accessibility, content consumption on the go, or for users who prefer audio over reading. The repository supports handling common ebook formats and generating outputs that combine audio plus caption metadata. By automating text-to-speech for arbitrary documents, abogen reduces the friction of producing audiobooks and could be integrated into larger workflows (e.g., batch converting a library of texts). -
3
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,... -
4
img2dataset
Easily turn large sets of image urls to an image dataset
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine. Also supports saving captions for url+caption datasets. Opt-out directives: Websites can pass the http headers X-Robots-Tag: noai, X-Robots-Tag: noindex , X-Robots-Tag: noimageai and X-Robots-Tag: noimageindex By default img2dataset will ignore images with such headers. -
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
5
claude-video
Give Claude the ability to watch any video
Claude Video is an agent skill that gives Claude and compatible coding assistants the ability to analyze video content. It accepts public video URLs or local video files, then extracts the information needed to answer user questions about what happened on screen and in the audio. The workflow checks captions first, downloads only what is necessary, extracts timestamped frames, and produces a transcript through native captions or Whisper fallback. It supports different detail levels so users... -
6
RealtimeSTT
A robust, efficient, low-latency speech-to-text library
RealtimeSTT is a Python-based realtime speech-to-text engine emphasizing low latency, wake-word detection, voice activity detection, and automatic speech segmentation. It provides asynchronous callbacks, nanosecond-precision timestamps, and CLI tools, suitable for building voice assistants, meeting transcribers, or live caption systems. -
7
Plyr
Simple HTML5, YouTube and Vimeo player
...Fullscreen - supports native fullscreen with fallback to "full window" modes. Picture-in-Picture - supports picture-in-picture mode. Multiple captions - support for multiple caption tracks. -
8
CLIP
CLIP, Predict the most relevant text snippet given an image
CLIP (Contrastive Language-Image Pretraining) is a neural model that links images and text in a shared embedding space, allowing zero-shot image classification, similarity search, and multimodal alignment. It was trained on large sets of (image, caption) pairs using a contrastive objective: images and their matching text are pulled together in embedding space, while mismatches are pushed apart. Once trained, you can give it any text labels and ask it to pick which label best matches a given image—even without explicit training for that classification task. The repository provides code for model architecture, preprocessing transforms, evaluation pipelines, and example inference scripts. ... -
9
YoutubeExplode
Abstraction layer over YouTube's internal API
YoutubeExplode is a .NET library that provides a high-level abstraction for interacting with YouTube data, enabling developers to retrieve metadata and download media streams programmatically. The project exposes a clean API that allows applications to query videos, playlists, channels, and search results without relying on the official YouTube Data API. Under the hood, the library parses raw page data and leverages reverse-engineered internal endpoints to obtain structured information and... -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
10
AiToEarn
Let's use AI to Earn
...The project supports matrix publishing to major global platforms like TikTok, YouTube, Instagram, Facebook, Pinterest, Twitter (X), and several Chinese social networks, enabling a “create once, publish everywhere” workflow. AI automation assists with tasks like title and caption creation, batch content generation, and optimization for each channel’s format and audience. Developers can run or extend AiToEarn locally using Node.js or via its desktop and web apps, and the open-source architecture encourages customization and community contributions. -
11
Verticals v3
Automated YouTube Shorts pipeline
Verticals v3 is an automated content generation workflow designed to create and process YouTube Shorts videos programmatically. It combines multiple tools and scripts to handle tasks such as downloading source material, editing clips, adding subtitles, and formatting output for vertical video platforms. The pipeline emphasizes automation, allowing users to produce short-form content at scale with minimal manual intervention. It integrates FFmpeg and other media processing tools to handle... -
12
OmniParser
A simple screen parsing tool towards pure vision based GUI agent
...To achieve this, OmniParser curates an interactable icon detection dataset containing 67,000 unique screenshot images labeled with bounding boxes of interactable icons derived from DOM trees. Additionally, a collection of 7,000 icon-description pairs is used to fine-tune a caption model that extracts the functional semantics of detected elements. Evaluations on benchmarks such as SeeClick, Mind2Web, and AITW demonstrate that OmniParser outperforms GPT-4V baselines, even when using only screenshot inputs without additional information. -
13
Qwen-Image-Layered
Qwen-Image-Layered: Layered Decomposition for Inherent Editablity
Qwen-Image-Layered is an extension of the Qwen series of multimodal models that introduces layered image understanding, enabling the model to reason about hierarchical visual structures — such as separating foreground, background, objects, and contextual layers within an image. This architecture allows richer semantic interpretation, enabling use cases such as scene decomposition, object-level editing, layered captioning, and more fine-grained multimodal reasoning than with flat image... -
14
DeepSeek VL2
Mixture-of-Experts Vision-Language Models for Advanced Multimodal
...It combines image and text inputs into a unified embedding / reasoning space so that you can query with text and image jointly (e.g. “What’s going on in this scene?” or “Generate a caption appropriate to context”). The model supports both image understanding (vision tasks) and multimodal reasoning, and is likely used as a component in agent systems to process visual inputs as context for downstream tasks. The repository includes evaluation results (e.g. image/text alignment scores, common VL benchmarks), configuration files, and model weights (where permitted). ... -
15
Gource
Software version control visualization
Software projects are displayed by Gource as an animated tree with the root directory of the project at its centre. Directories appear as branches with files as leaves. Developers can be seen working on the tree at the times they contributed to the project. Gource includes built-in log generation support for Git, Mercurial, Bazaar and SVN. Gource can also parse logs produced by several third party tools for CVS repositories. Gource is a visualization tool for source control repositories. The... -
16
4M
4M: Massively Multimodal Masked Modeling
4M is a training framework for “any-to-any” vision foundation models that uses tokenization and masking to scale across many modalities and tasks. The same model family can classify, segment, detect, caption, and even generate images, with a single interface for both discriminative and generative use. The repository releases code and models for multiple variants (e.g., 4M-7 and 4M-21), emphasizing transfer to unseen tasks and modalities. Training/inference configs and issues discuss things like depth tokenizers, input masks for generation, and CUDA build questions, signaling active research iteration. ... -
17
OpenAI DALL·E AsyncImage SwiftUI
OpenAI swift async text to image for SwiftUI app using OpenAI
...You need to have Xcode 13 installed in order to have access to Documentation Compiler (DocC) OpenAI's text-to-image model DALL-E 2 is a recent example of diffusion models. It uses diffusion models for both the model's prior (which produces an image embedding given a text caption) and the decoder that generates the final image. In machine learning, diffusion models, also known as diffusion probabilistic models, are a class of latent variable models. They are Markov chains trained using variational inference. The goal of diffusion models is to learn the latent structure of a dataset by modeling the way in which data points diffuse through the latent space. -
18
Exile is a Python based image collection manager application. Easily add metadata to photos, inluding Caption, People, Event, Location and Tags. No external database: stores metadata in Exif/IPTC/Xmp tags. Three level categorization for easy photo sorting/management Clone GPS data between files.
-
19
OpenClipper
Free, open-source Opus Clip alternative for Windows.
...CLIPPING Auto: create 15s, 30s, 45s, 1m, or custom clips from the transcript Manual: click two words to set in/out points MCP: let an agent choose clips by word index with live preview Open the full GrepCut Studio editor from Clipper OVERLAYS Animated caption presets with live preview Adjust position, size, and words per line Add a logo or handle; control placement and opacity TRANSCRIPTION Run Parakeet or Whisper v3 Turbo locally, with optional MDX vocal isolation Or use your Groq/OpenRouter API key AUTOREFRAME Face and subject tracking for 9:16, 4:5, 1:1, and 16:9 Split view when two people won’t fit in one crop RENDER QUEUE Choose formats per clip Export at source quality, 1080p, or 720p PUBLISH Publish directly to TikTok and YouTube -
20
WinExplorer is a utility that shows all system's windows in hierarchical display. For every window in the hierarchy, you can view its properties, like handle, class name, caption, size, position and more. You can also modify some properties, like Caption and Visible/Enabled. This utility is released as freeware with full source code. You can freely use, distribute, and modify the source code of this utility without restrictions. However, if you release to the public a modified version of this utility, you should specify the original copyright notice.
-
21
ShortGeek
Free short video maker for Windows - article in, narrated short out
ShortGeek turns one of your guides, an RSS feed or a bare topic into a narrated, captioned vertical short, rendered on your own machine. Pick a source, review the script before anything renders, choose a voice and a look, then let it render. Hook, beats and call to action are all editable first. Captions are word level and timed from the voice engine rather than estimated, in three styles. Eight backgrounds are generated in code, frame by frame, so nothing is AI art, and you can drop... -
22
CogVLM
A state-of-the-art open visual language model
...It includes checkpoints for chat, base, and grounding variants, plus recipes for model-parallel inference and LoRA fine-tuning. The documentation covers task prompts for general dialogue, visual grounding (box→caption, caption→box, caption+boxes), and GUI agent workflows that produce structured actions with bounding boxes. -
23
blackvideo-mini-player
A standalone lightweight auxiliary CLI video player for BlackVideo.
Lightweight cross-platform video player (Ada + SDL2 + FFmpeg). Support player for the BlackVideo. Works standalone via CLI or right-click on any video file. Usage Method 1 — Command Line Step 1. Unzip blackvideo-mini-player-v2.3.0.win.zip Step 2. Open the build\ folder, then type cmd directly in the address bar and press Enter — this opens a terminal already in that folder. Alternatively: open Command Prompt anywhere and use cd with the copied path: cd... -
24
DeepSeek VL
Towards Real-World Vision-Language Understanding
DeepSeek-VL is DeepSeek’s initial vision-language model that anchors their multimodal stack. It enables understanding and generation across visual and textual modalities—meaning it can process an image + a prompt, answer questions about images, caption, classify, or reason about visuals in context. The model is likely used internally as the visual encoder backbone for agent use cases, to ground perception in downstream tasks (e.g. answering questions about a screenshot). The repository includes model weights (or pointers to them), evaluation metrics on standard vision + language benchmarks, and configuration or architecture files. ... -
25
Krajee
An enhanced HTML 5 file input for Bootstrap 5.x/4.x./3.x
An enhanced HTML 5 file input for Bootstrap 5.x or Bootstrap 4.x or Bootstrap 3.x with file preview for various files, offers multiple selection, and more. The plugin allows you a simple way to setup an advanced file picker/upload control built to work specially with Bootstrap CSS3 styles. It enhances the file input functionality further, by offering support to preview a wide variety of files i.e. images, text, html, video, audio, flash, and objects. In addition, it includes AJAX based...
