> ## Documentation Index > Fetch the complete documentation index at: https://docs.eversince.ai/llms.txt > Use this file to discover all available pages before exploring further. # auto reframe > Choose what a clip shows when its picture does not match the box it fills (a 16:9 shot on a 9:16 timeline is centre-cropped by default). view shows one named area of the source, zoomed or not, for the whole clip. Otherwise the crop follows the person, or the largest thing in shot with subject any, cutting rather than panning; two people hold on the larger, or with follow speaker cut to whoever is talking (needs speakers on the recording). A picture that fits, or with nobody found, stays centred and says so. A clip whose subject has not been read yet is read in the background: the answer carries job_id, and the crop lands on the timeline when it finishes (get_jobs). Writes the focus track only, so a punch-in and a camera move stack on it. Reading a subject: cloud processing. ## OpenAPI ````yaml /openapi.json post /tools/auto_reframe openapi: 3.1.0 info: title: Eversince API version: '1' description: >- Every Eversince tool as one POST call, plus the routes beside them: the tool list, account and keys, uploads, webhooks and models. The prose is at https://docs.eversince.ai. servers: - url: https://eversince.ai/api/v1 security: - bearer: [] tags: - name: Discovery description: The tool list, the same on the MCP server, the REST API and the CLI. - name: Workspace description: Jobs, balances, settings, templates, skills and the overview. - name: Library description: >- Items, search, import, reading media, comments, boards, calendars, the brand kit and public links. - name: Timeline description: 'Video editing: timelines, clips, captions, sound, language and rendering.' - name: Canvas description: 'Still editing: canvases, slides, layers and rendering.' - name: Generation description: Image, video and audio generation, upscaling, cutouts and models. - name: Research description: 'What platforms publish: pulling and keeping posts.' - name: Account description: Balances, keys, workspaces and script sessions. - name: Uploads description: Files into the library by presigned upload or by URL. - name: Webhooks description: Job results posted to a URL as they complete. - name: Models description: Generation models and cost estimates. paths: /tools/auto_reframe: post: tags: - Timeline summary: auto reframe description: >- Choose what a clip shows when its picture does not match the box it fills (a 16:9 shot on a 9:16 timeline is centre-cropped by default). view shows one named area of the source, zoomed or not, for the whole clip. Otherwise the crop follows the person, or the largest thing in shot with subject any, cutting rather than panning; two people hold on the larger, or with follow speaker cut to whoever is talking (needs speakers on the recording). A picture that fits, or with nobody found, stays centred and says so. A clip whose subject has not been read yet is read in the background: the answer carries job_id, and the crop lands on the timeline when it finishes (get_jobs). Writes the focus track only, so a punch-in and a camera move stack on it. Reading a subject: cloud processing. operationId: auto_reframe parameters: - $ref: '#/components/parameters/IdempotencyKey' - $ref: '#/components/parameters/WorkspaceId' requestBody: required: true content: application/json: schema: type: object properties: timeline_id: type: string description: The timeline id. clip_id: description: >- The video clip to reframe. Absent: every video clip on the timeline. type: string view: description: >- Show one area of the source for the whole clip: its centre as fractions of the source (x 0 left, y 0 top) and, to zoom, its width as a fraction of the source width; no width shows as much as the box holds. Kept inside the picture, up to 5x. Needs clip_id (video or image). Replaces the clip's scale, pan and focus track. type: object properties: x: type: number minimum: 0 maximum: 1 'y': type: number minimum: 0 maximum: 1 width: type: number exclusiveMinimum: 0 maximum: 1 required: - x - 'y' subject: description: >- What the crop follows: people (default; a person's head is what it aims at), or any subject, the largest thing detected when no person is in shot. type: string enum: - person - any follow: description: >- Where two people share the frame: speaker cuts the crop to whoever is talking, from a speaking-face read at a dozen of each voice's turns, once per recording. Needs speakers on the recording; where it cannot tell, the crop stays centred and says so. Default holds both. type: string enum: - subject - speaker if_revision: description: >- The revision get_timeline returned. A stale one fails with revision_conflict instead of applying; so does no revision once a user edited the timeline in the app since this connection last read it. anyOf: - type: string - type: integer context: description: 'Optional: one sentence shown to the user beside this action.' type: string maxLength: 600 required: - timeline_id responses: '200': description: >- Done, or a job started for work that runs longer (follow it with get_jobs). content: application/json: schema: type: object required: - ok - data - meta properties: ok: const: true data: type: object additionalProperties: true meta: type: object properties: request_id: type: string cost: $ref: '#/components/schemas/Cost' cloud_processing: $ref: '#/components/schemas/CloudProcessing' media: type: array items: type: object additionalProperties: true default: $ref: '#/components/responses/Error' components: parameters: IdempotencyKey: name: Idempotency-Key in: header required: false schema: type: string description: >- Retry a paid dispatch safely: the same key returns the job already dispatched instead of charging again. WorkspaceId: name: x-workspace-id in: header required: false schema: type: string description: The workspace this one call acts in, when it is not the key's own. schemas: Cost: type: object description: AI credits the call cost. additionalProperties: true CloudProcessing: type: object description: Cloud processing the call used, and what is left. properties: ran_on: const: cloud minutes: type: number queued_minutes: type: number left_minutes: type: number bought_minutes: type: number note: type: string Error: type: object required: - ok - error properties: ok: const: false error: type: object required: - code - message - retryable properties: code: type: string message: type: string description: What went wrong, in words to act on. retryable: type: boolean suggested_action: type: string description: The next step that works. cloud_processing: $ref: '#/components/schemas/CloudProcessing' responses: Error: description: The call was refused or failed. content: application/json: schema: $ref: '#/components/schemas/Error' securitySchemes: bearer: type: http scheme: bearer description: >- An API key (es_live_…) from Settings, under API keys, or an OAuth access token. ````