Что умеет

Create Upload: Only for a video file on the caller's side, at most 2 GB. Returns a PUT-only upload URL for one object, valid for one hour; PUT the raw bytes to it, then call caption_video with the ret

Caption Video: Start captioning one video. Pass exactly one source: inputUrl, a direct https link to a video file (platform pages such as YouTube or TikTok are refused), or jobId from create_upload af

Get Caption Job: Poll a job. While it runs, retryAfterSeconds says how long to wait before calling again. When status is completed, artifacts holds signed links to the captioned MP4, SRT, VTT, ASS and

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.

CaptionPipe

Что умеет

Какие данные видит

Нужен ли аккаунт

create_upload	Only for a video file on the caller's side, at most 2 GB. Returns a PUT-only upload URL for one object, valid for one hour; PUT the raw bytes to it, then call caption_video with the returned jobId. Pass contentLength if you know the file's size in bytes and the URL is bound to it; leave it out if you do not. If the video is already at a direct https URL, skip this tool entirely and pass inputUrl to caption_video. A retry is safe only when it carries the same idempotencyKey; without one, each call creates a new upload.
caption_video	Start captioning one video. Pass exactly one source: inputUrl, a direct https link to a video file (platform pages such as YouTube or TikTok are refused), or jobId from create_upload after the bytes are uploaded. Choose a preset: highlight (the spoken word takes the accent), clean (white with an outline) or boxed (a plate behind the line). Optionally send a dictionary of names to spell right and a language. Returns a jobId in status probing; poll it with get_caption_job. The balance is charged by the whole second once the duration is known, and nothing is charged if the job fails.
get_caption_job	Poll a job. While it runs, retryAfterSeconds says how long to wait before calling again. When status is completed, artifacts holds signed links to the captioned MP4, SRT, VTT, ASS and words.json, valid until expiresAt (24 hours after completion), and chargedSeconds is final. After a render_captions call, render says which version was asked for last and whether it is still rendering, done, or failed; the links always belong to the newest finished version, and preset describes the newest request. When status is failed, error says why and nothing was charged. dictionaryCapacityApplied is the dictionary capacity the speech vendor honoured (1000 on the primary vendor, 0 on the fallback), not a count of terms. Every response includes the caller's balance.
render_captions	Burn the same video again from edited words. Send the job's words.json with corrections applied, every word with its startMs and endMs in order (keep confidence if you want it in the new words.json); no speech model runs, what you send is what gets burned. Optionally change the preset or the highlight colour. Free within the job's allowance (3 on a paid account, 1 on the trial) and within 24 hours of completion. Returns the job at once with render.status accepted; poll get_caption_job until it is completed, when the artifact links switch to the new version. A retry is safe only when it carries the same idempotencyKey and the same body; without a key, each accepted call reserves a re-render from the allowance. Completion spends it; failure returns it. After 3 failed re-renders the job is paused for investigation, with rerenderFailureLimitReached true; do not automatically retry. Re-renders count toward the account's concurrent job limit while they run.