Clippie AI logo
Get Started
Browse the docs

Developers / Docs / Templates

Create captions video

Adds styled, word-by-word captions to your own video (fileId from upload_file, or an https url; up to 30 minutes) and saves it as a Captions project. Spends caption minutes for the video's length, as the app does (1 per minute of video); aiEmojis are free. By default it is a draft: the finished job has stills, previewUrl (plays it in the browser), editorUrl and the words with their indexes. Restyle it with update_video, then render it with render_video. render: true goes straight to the MP4 and also spends export minutes. Run estimate_cost (or dryRun: true) first and confirm the cost. Wait for the job with get_job (waitSeconds).

Paste it into any AI assistant. The shortcuts open with the prompt typed in; nothing is sent until you press enter.

At a glance

  • REST
    POST https://api.clippie.ai/v1/videos/captions
  • MCP tool
    create_captions_video
  • Scope
    create
  • Cost
    Spends credits or minutes, at the same prices as the app. Send "dryRun": true (or call estimate_cost) first to see the exact cost without spending anything.
  • Limit bucket
    transcribe (see Rate limits)

Parameters

  • fileId
    In:
    body
    Type:
    string
    Required:
    No
    Description:
    A video file id (file_…) from upload_file or POST /v1/files. Give fileId or url. 1-80 chars.
  • url
    In:
    body
    Type:
    string
    Required:
    No
    Description:
    A public https URL of the video (copied into Clippie first, up to 100 MB; upload bigger files). Give fileId or url. 1-2048 chars.
  • title
    In:
    body
    Type:
    string
    Required:
    No
    Description:
    Project and file name. Defaults to the video's file name. 1-120 chars.
  • captionStyleId
    In:
    body
    Type:
    integer
    Required:
    No
    Description:
    Caption style id from list_caption_styles. Defaults to your brand caption style, else 2. 1-17.
  • captionPosition
    In:
    body
    Type:
    number
    Required:
    No
    Description:
    Vertical position of the captions, 0 (top) to 100 (bottom). Default 50. 0-100.
  • captionSize
    In:
    body
    Type:
    number
    Required:
    No
    Description:
    Caption size, 0-100. Default 50. 0-100.
  • textStyle
    In:
    body
    Type:
    object
    Required:
    No
    Description:
    Colour, case, outline and shadow over the caption style.
  • language
    In:
    body
    Type:
    string
    Required:
    No
    Description:
    Spoken language code from list_languages (e.g. "en", "es"). Default: detected. Up to 10 chars.
  • ratio
    In:
    body
    Type:
    string
    Required:
    No
    Description:
    Frame shape. "original" (default) follows the video: landscape footage gets 16:9, anything else 9:16. One of original, 9:16, 16:9.
  • aiEmojis
    In:
    body
    Type:
    boolean
    Required:
    No
    Description:
    Default false. true adds AI-picked emojis to the caption lines (free).
  • render
    In:
    body
    Type:
    boolean
    Required:
    No
    Description:
    Default false: a draft you can preview (stills, previewUrl) and restyle with update_video before render_video. true renders the MP4 straight away (spends export minutes too).
  • dryRun
    In:
    body
    Type:
    boolean
    Required:
    No
    Description:
    Check the request and return { estimate } (credits and minutes) without spending anything.
  • webhookUrl
    In:
    body
    Type:
    string (URL)
    Required:
    No
    Description:
    https URL that receives job.completed / job.failed, signed with your webhook secret. Up to 2048 chars.
  • Idempotency-Key
    In:
    header
    Type:
    string
    Required:
    No
    Description:
    Retry-safe key: a retry with the same key and body within 24 hours returns the first job instead of starting (and charging) again. The same key with a different body is a 409. MCP clients pass it as the idempotencyKey argument. 1-255 chars. MCP: idempotencyKey.

Example

curl
# 1. Dry run: the exact cost, nothing is spent.
curl https://api.clippie.ai/v1/videos/captions \
  -H "Authorization: Bearer $CLIPPIE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "dryRun": true
  }'
# => { "dryRun": true, "estimate": { "credits": ..., "minutes": { ... }, "wouldSucceed": true } }

# 2. The real call. Keep the key and send the same one if you retry, so it is never charged twice.
KEY=$(uuidgen)
curl https://api.clippie.ai/v1/videos/captions \
  -H "Authorization: Bearer $CLIPPIE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $KEY" \
  -d '{}'
# => 202 { "job": { "id": "job_...", "status": "queued", ... } }

Response

202 { job }: the job, straight away. Wait for it with Get job (?wait=30) or a webhookUrl; see Jobs and waiting. With "dryRun": true the answer is 200 { dryRun: true, estimate } and nothing is started.

202 Accepted
{
  "job": {
    "id": "job_abc123",
    "object": "job",
    "kind": "create_captions_video",
    "status": "queued",
    "step": null,
    "progress": null,
    "input": {
      "prompt": "The lost library of Alexandria"
    },
    "output": null,
    "cost": {
      "credits": 0,
      "minutes": {
        "voiceover": 1,
        "captions": 1,
        "export": 1
      }
    },
    "error": null,
    "source": "api",
    "webhookUrl": null,
    "createdAt": "2026-10-24T12:00:00.000Z",
    "startedAt": null,
    "completedAt": null
  }
}
Dry run (200), shape only
{
  "dryRun": true,
  "estimate": {
    "credits": 0,
    "minutes": {
      "voiceover": 0,
      "captions": 0,
      "export": 0
    },
    "wouldSucceed": true
  }
}

From an MCP client

Your AI calls create_captions_video with the same fields as JSON arguments, plus idempotencyKey instead of the header. See MCP server to connect one.

tools/call
{
  "name": "create_captions_video",
  "arguments": {
    "idempotencyKey": "a-unique-key-per-thing-you-make"
  }
}