Multi Upload Tool AI API

Texts and animated subtitles generated from what a video says. Billed in AI minutes, then credits.

GitHub OpenAPI

Operations 3

POST /ai/post-text Generate title, caption and hashtags from a video #
POST /ai/captions Burn animated subtitles into a video #
GET /ai/captions/{jobId} Get a subtitle render #

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/multi-upload-tool-com:multi-upload-tool-com-ai-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

multi-upload-tool-com-ai-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: Multi Upload Tool AI API
  version: 1.0.0
  summary: Publish and schedule video and photo posts to TikTok, YouTube, Instagram, Facebook, LinkedIn, Pinterest, Bluesky and Threads from one API.
  description: 'REST API for the Multi Upload Tool platform.


    Upload a video or photo once and publish it to one or many connected social accounts, immediately or on a schedule. The API also covers connected-account management, upload history, per-account daily limits, webhooks, teams, white-label connection links, short links and custom domains.


    ## Authentication


    Every endpoint requires an API token sent in the `x-api-key` header. Tokens are created from the dashboard and look like `kmb_`.


    ```

    x-api-key: kmb_0123456789abcdef...

    ```


    ## Permission model


    A token carries **scopes**, chosen when it is created in the dashboard. `*` grants everything: it is what every token created before scopes existed holds, and what a token created without a list gets. Otherwise the token holds `resource:action` scopes — `posts:read`, `posts:write`, `posts:publish`, `accounts:read`, `accounts:write`, `analytics:read`, `pools:read`, `pools:write`, `webhooks:read`, `webhooks:write`, `team:read`, `team:write`, `links:read`, `links:write`. `write` includes `read`, and `posts:publish` includes `posts:write`. A token with `posts:write` but not `posts:publish` can create posts, but they are always held for approval. Each operation states what it needs in `x-required-scope`; a call without it returns `403` with `code: INSUFFICIENT_SCOPE` and `requiredScope`.


    On top of scopes, **team scoping** applies.


    - A token created against a team is permanently pinned to that team. It can only read and write that team''s resources, and it is revoked automatically if the user leaves the team.

    - An unscoped token may target a team per-request with the `X-Team-ID` header. Membership is verified on every call.

    - Inside a team, the member''s role (`OWNER`, `ADMIN`, `MEMBER`) gates privileged operations. Members cannot create webhooks; only owners and admins can invite or remove members; only an owner can remove an admin.


    Treat an API token as a credential and store it accordingly; give each integration only the scopes it needs.


    ## Large media


    A file part sent to `POST /upload` must stay under 100 MB, an edge limit on the request body rather than a platform one. For anything larger, call `POST /upload/presign` to get URLs that put the bytes straight into storage, then publish by passing the returned `bucketUrl` (preferred for large video) or `accessUrl` in the `video`, `photo` or `file` field.


    ## Rate limits


    Limits are applied per IP and per endpoint group; exceeding one returns `429`. The tightest limits are on writes: 50 requests / 15 min for `POST /upload`, 20 requests / 15 min for `POST /upload/bulk` and for destructive operations. Reads are typically 100 requests / 5-15 min. A single IP may also present at most 10 distinct API tokens per hour.


    ## Errors


    Errors return a JSON body of the form `{ "success": false, "error": "..." }`. Validation failures on `POST /upload` additionally return a per-field `errors` array.'
  termsOfService: https://multi-upload-tool.com/terms
  contact:
    name: Multi Upload Tool support
    url: https://multi-upload-tool.com/about
    email: support@multi-upload-tool.com
servers:
- url: https://api.multi-upload-tool.com/api/v1
  description: Production
security:
- apiKey: []
tags:
- name: AI
  description: Texts and animated subtitles generated from what a video says. Billed in AI minutes, then credits.
paths:
  /ai/post-text:
    post:
      tags:
      - AI
      summary: Generate title, caption and hashtags from a video
      description: 'Transcribes the video and writes, per platform, a title, a caption and hashtags from what is said in it, in the video''s language, reusing your best-performing hashtags. Returns text only: pass it to POST /upload. Costs 1 AI minute per started minute of video: the plan''s monthly AI minutes first, then purchased credits (see GET /x-credits, field ai). A video is transcribed and billed once: generating its texts and then its subtitles pays once. Videos up to 30 minutes. In a team, the team owner''s plan pays.'
      operationId: generatePostText
      x-required-scope: posts:write
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - mediaUrl
              - platforms
              properties:
                mediaUrl:
                  type: string
                  description: URL of a video you uploaded (POST /upload/presign or a previous upload).
                platforms:
                  type: array
                  items:
                    type: string
                  minItems: 1
                  maxItems: 20
                  example:
                  - tiktok
                  - instagram
                  - youtube
                accountIds:
                  type: array
                  items:
                    type: string
                  description: 'Accounts the post will go to: their best hashtags are reused.'
                draft:
                  type: string
                  maxLength: 5000
                  description: Your own draft or instructions to take into account.
      responses:
        '200':
          description: Texts per platform, the detected language and the minutes charged (0 when the video was already transcribed).
          content:
            application/json:
              schema:
                type: object
                properties:
                  success:
                    type: boolean
                  data:
                    type: object
                    additionalProperties: true
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '422':
          $ref: '#/components/responses/ValidationError'
        '429':
          $ref: '#/components/responses/RateLimited'
        '402':
          description: Not enough AI minutes or credits for this video.
  /ai/captions:
    post:
      tags:
      - AI
      summary: Burn animated subtitles into a video
      description: 'Transcribes the video, lets the AI pick keywords and emojis, then renders the subtitles into a new video in the background (usually under a minute). Poll GET /ai/captions/{jobId}, then publish the returned url instead of the original video. Costs 1 AI minute per started minute of video: the plan''s monthly AI minutes first, then purchased credits (see GET /x-credits, field ai). A video is transcribed and billed once: generating its texts and then its subtitles pays once. Videos up to 30 minutes. In a team, the team owner''s plan pays. The render itself is included.'
      operationId: addCaptions
      x-required-scope: posts:write
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - mediaUrl
              properties:
                mediaUrl:
                  type: string
                  description: URL of a video you uploaded (POST /upload/presign or a previous upload).
                theme:
                  type: string
                  enum:
                  - hormozi
                  - beast
                  - box
                  - single
                  - minimal
                  - podcast
                  default: hormozi
                position:
                  type: number
                  minimum: 0
                  maximum: 1
                  description: 'Vertical centre of the line: 0 top, 1 bottom. Default depends on the theme.'
                scale:
                  type: number
                  minimum: 0.5
                  maximum: 2
                  default: 1
                  description: Text size multiplier.
                wordsPerLine:
                  type: integer
                  minimum: 1
                  maximum: 8
                  description: More words per line = calmer pace. Default depends on the theme.
                highlights:
                  type: boolean
                  default: true
                  description: Keywords in colour.
                emojis:
                  type: boolean
                  default: false
                  description: One emoji above each line when the AI picked one.
                emojiStyle:
                  type: string
                  enum:
                  - noto
                  - fluent
                  default: noto
                  description: noto = flat Google emojis, fluent = 3D.
                colors:
                  type: object
                  properties:
                    text:
                      type: string
                      pattern: ^#[0-9A-Fa-f]{6}$
                    active:
                      type: string
                      pattern: ^#[0-9A-Fa-f]{6}$
                    highlight:
                      type: string
                      pattern: ^#[0-9A-Fa-f]{6}$
                  description: Override the theme's text, spoken-word and keyword colours.
                enter:
                  type: string
                  enum:
                  - pop
                  - fade
                  - none
                  description: How a line comes in. Default depends on the theme.
                exit:
                  type: string
                  enum:
                  - fade
                  - none
                  default: none
      responses:
        '200':
          description: The render job.
          content:
            application/json:
              schema:
                type: object
                properties:
                  success:
                    type: boolean
                  data:
                    type: object
                    properties:
                      jobId:
                        type: string
                      minutesCharged:
                        type: integer
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '422':
          $ref: '#/components/responses/ValidationError'
        '429':
          $ref: '#/components/responses/RateLimited'
        '402':
          description: Not enough AI minutes or credits for this video.
  /ai/captions/{jobId}:
    get:
      tags:
      - AI
      summary: Get a subtitle render
      description: 'State of a render started with POST /ai/captions: waiting, active, completed (with url, the captioned video) or failed (with error).'
      operationId: getCaptionsRender
      x-required-scope: posts:read
      parameters:
      - name: jobId
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Render state.
          content:
            application/json:
              schema:
                type: object
                properties:
                  success:
                    type: boolean
                  data:
                    type: object
                    properties:
                      state:
                        type: string
                        example: completed
                      url:
                        type: string
                      error:
                        type: string
        '401':
          $ref: '#/components/responses/Unauthorized'
        '404':
          $ref: '#/components/responses/NotFound'
        '429':
          $ref: '#/components/responses/RateLimited'
components:
  responses:
    NotFound:
      description: No such resource, or it does not belong to the caller.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    ValidationError:
      description: The request body or parameters were rejected.
      content:
        application/json:
          schema:
            oneOf:
            - $ref: '#/components/schemas/Error'
            - $ref: '#/components/schemas/FieldValidationError'
    Unauthorized:
      description: The API key is missing, invalid, revoked or expired.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Forbidden:
      description: The token is valid but not permitted to act on this resource, usually because of team scoping or the caller's team role.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    RateLimited:
      description: Too many requests for this endpoint group.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  schemas:
    FieldValidationError:
      type: object
      required:
      - success
      - message
      - errors
      properties:
        success:
          const: false
        message:
          const: Validation Error
        errors:
          type: array
          items:
            type: object
            properties:
              path:
                type: string
              message:
                type: string
              summary:
                type: string
    Error:
      type: object
      required:
      - success
      - error
      properties:
        success:
          const: false
        error:
          type: string
          description: Human-readable failure reason.
        statusCode:
          type: integer
  securitySchemes:
    apiKey:
      type: apiKey
      in: header
      name: x-api-key
      description: 'API token created from the dashboard, in the form `kmb_<64 hex characters>`.


        A token carries a list of scopes, chosen when it is created: `*` (everything — every token created before scopes existed, and any token created without a list) or `resource:action` scopes such as `posts:read` or `analytics:read`. Each operation states the scope it needs in `x-required-scope`; a token without it gets `403` with `code: INSUFFICIENT_SCOPE`. A token with `posts:write` but not `posts:publish` can create posts, which are always held for approval. On top of scopes, team scoping applies: baked into the token at creation time or requested per-call with `X-Team-ID`. Store it as you would a password.'
externalDocs:
  description: Full API documentation
  url: https://docs.multi-upload-tool.com/api-reference