WebCull is a web-based bookmark manager, with browser extensions on Chrome, Firefox, Edge, Brave, Opera, and more. Designed to provide a secure, privacy-focused solution for organizing and accessing web links, WebCull aims to address privacy concerns associated with traditional bookmark management tools by offering end-to-end encryption (E2EE) and an ad-free user experience. The service is compatible across various browsers and devices, ensuring seamless synchronization for its users.

• Features Cross-Device Synchronization: The service allows users to synchronize their bookmarks across multiple devices, including desktops, laptops, tablets, and smartphones. This feature is designed to provide a consistent user experience regardless of the device being used. Ad-Free Experience: Unlike many other bookmark managers, WebCull is completely ad-free. This decision enhances user experience by eliminating distractions and potential privacy invasions associated with targeted advertising. Privacy and Data Security: WebCull is committed to maintaining user privacy and data security. The platform does not track user activity or collect unnecessary personal information. All data stored on WebCull is encrypted, and the company adheres to strict data protection policies. Pro Package: WebCull's standout feature is its implementation of end-to-end encryption (E2EE), ensuring that only the user can decrypt their bookmarks. This security measure prevents unauthorized access, even from WebCull's own servers. The encryption keys are stored exclusively on the user's devices, aligning with the strictest privacy principles.

TranscriptFetch is one API for getting text out of video and web content.

Send a URL from YouTube, TikTok, Instagram, X or Facebook and get back clean, timestamped text. Send any web page and get clean Markdown. One endpoint, one response shape, one API key.

The part that actually matters

Most short-form video has no caption track to download. TikTok's auto-captions are opt-in per upload, Instagram never publishes a downloadable track, and a large share of captions on both platforms are burned into the video frames where no parser can read them.

When there is no caption track, TranscriptFetch transcribes the audio instead. Same endpoint, same response, so your code never branches on which method produced the text.

What you get back

• A joined text field for feeding a model or a search index
• A segments array with per-cue start times and durations, so subtitles and jump-to-moment links are a formatting step rather than another integration
• Consistent output whether the text came from captions or speech recognition

Built for pipelines and agents

• MCP server so Claude, Cursor and other MCP clients can fetch transcripts as a tool mid-conversation
• Python and JavaScript SDKs
• Batch endpoint for up to 50 videos in a single call
• Channel, playlist and keyword-search endpoints for ingesting at scale

Pricing

100 free credits on signup, no card required. One credit per successful response. Failed, blocked and empty results are never charged, which matters on short-form video where a meaningful share of any batch is music with no speech in it.