Deroom is an AI room design tool that takes a photo of your real space and returns a photorealistic redesign in under a minute.

Generic AI image generators hallucinate room layouts — windows move, walls disappear, ceilings drop. Deroom is built differently: it analyzes the actual geometry of the room you upload (corners, openings, light sources) and applies the new style on top of that real structure. The result looks like a photo of your room, restyled — not someone else's.

What it does

• 9 room types — bedroom, kitchen, bathroom, living room, home office, closet, exterior, garden, and landscape.
• 12 curated design styles — Scandinavian, Japandi, Modern, Minimalist, Mid-Century, Industrial, Bohemian, Coastal, and more.
• 5 action modes — instead of always doing a full redesign, you can:
  • Full Redesign — reimagine the entire room
  • Recolor Only — change wall and finish colors, keep everything else
  • Furniture Swap — replace furniture, keep the layout
  • Quick Refresh — minor updates to textures and decor
  • Declutter — clean and tidy the existing space

Who it's for

• Home sellers and real-estate agents staging photos before listing
• Renters previewing how new colors or furniture will look before buying
• Interior designers iterating concepts with clients in real time
• Homeowners exploring renovation ideas without paying for mockups

Output and pricing

Free tier lets you try the product without commitment. Paid plans unlock 4K resolution, no watermark, and a commercial-use license — practical for agents and designers who need outputs in client-facing decks. Pricing is credit-based: a single generation costs 10 credits.

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.