SmitheryListed

CaptionPipe

Give CaptionPipe a video and it gives the video back with the captions burned in. One call does the whole thing: send a direct https link or upload the file, pick a caption style, and poll until it is done. Nothing to install. There is no FFmpeg to set up, no speech model to download, no local render. The server is hosted at api.captionpipe.com and speaks MCP over streamable HTTP, or plain HTTP if you would rather call it as a REST API. Nothing to subscribe to. Minutes are prepaid: $10 buys 250 minutes and they never expire. There is no monthly plan, nothing renews, and a failed job is not charged. New accounts get 5 free minutes. Four tools, not a toolbox. create_upload, caption_video, get_caption_job, render_captions. An agent does not have to choose between ninety ways to call FFmpeg. When a word comes out wrong, fix it. Every finished job returns word-level timings alongside the video. Send the corrected words back to render_captions and the video is burned again from exactly those words, free, up to three times per job within 24 hours. No speech model runs the second time, so what you send is what gets burned. Every job returns the burned MP4 plus SRT, VTT, ASS and words.json. Three caption styles. Inputs up to 2 GB and 30 minutes. Named-term dictionary so proper nouns are spelled right the first time. Media and captions are deleted 24 hours after the job finishes.

First seen 2 Oct 2026. Evidence as of 5 Oct 2026.