> ## 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. # cut clips > Cut many moments out of one recording at once: each span becomes its own clip, a timeline of its own inside the project, shaped, punched in on the words, cropped to the subject and captioned in one look. timeline_id is the project: any timeline of the workspace, usually one made for the set with manage_timelines create; clips of a project carry parent_id. In and out points move up to 1.2 seconds onto the nearest word edge when the recording has stored words (transcribe_media with ref reads them; without them spans are cut as given). Each clip that lands is returned with its timeline_id, name and landed span; a span the project already holds comes back in skipped, and one that could not be cut in failed. The first cut puts the set on the workspace feed. For one clip, edit_timeline addClip with source. Free, except captioning a recording without stored words and reading a subject for the crop: cloud processing. ## OpenAPI ````yaml /openapi.json post /tools/cut_clips 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/cut_clips: post: tags: - Timeline summary: cut clips description: >- Cut many moments out of one recording at once: each span becomes its own clip, a timeline of its own inside the project, shaped, punched in on the words, cropped to the subject and captioned in one look. timeline_id is the project: any timeline of the workspace, usually one made for the set with manage_timelines create; clips of a project carry parent_id. In and out points move up to 1.2 seconds onto the nearest word edge when the recording has stored words (transcribe_media with ref reads them; without them spans are cut as given). Each clip that lands is returned with its timeline_id, name and landed span; a span the project already holds comes back in skipped, and one that could not be cut in failed. The first cut puts the set on the workspace feed. For one clip, edit_timeline addClip with source. Free, except captioning a recording without stored words and reading a subject for the crop: cloud processing. operationId: cut_clips 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 project the clips land in: any timeline, empty or not, or a clip already in it. The recording itself is ref. ref: type: string description: The recording being cut, as a library ref. clips: minItems: 1 maxItems: 50 type: array items: type: object properties: source: type: array prefixItems: - type: number - type: number description: >- [start_seconds, end_seconds] in the recording, as the transcript and search_footage give them. name: description: >- What this clip is called, shown on its tab and its tile. Unnamed clips are numbered. type: string maxLength: 80 note: description: >- One line on why this moment, drawn under its tile when the set is published. type: string maxLength: 280 platforms: description: >- Where this cut goes: tiktok (9:16), instagram-reels (9:16), instagram-feed (1:1), youtube-shorts (9:16), youtube (16:9), facebook-reels (9:16), facebook-feed (1:1), x (16:9), threads (9:16), linkedin (1:1), pinterest (9:16). The first sets the shape unless aspect is given; all are drawn as marks under the tile. maxItems: 6 type: array items: type: string aspect: description: This clip's shape, over its platform's and the set's. type: string enum: - '16:9' - '9:16' - '21:9' - '9:21' - '1:1' - '4:3' - '3:4' - '3:2' - '2:3' - '5:4' - '4:5' hook: description: >- A line shown for the clip's first seconds, in the set's hook_style. Only where this moment wants one. type: string maxLength: 60 score: description: >- How sure you are this moment works for what the user wants, out of ten. Shown on the tile. type: integer minimum: 0 maximum: 10 required: - source description: >- The moments, in the order they should be numbered. Up to 50 a call. aspect: description: >- The shape every clip is cut at, 9:16 for shorts. Absent leaves each clip at the project's. type: string enum: - '16:9' - '9:16' - '21:9' - '9:21' - '1:1' - '4:3' - '3:4' - '3:2' - '2:3' - '5:4' - '4:5' captions: description: >- Caption every clip in this look: a template saved for the workspace, or a built-in one: Subtitles, Kinetic, One word, Karaoke, Broadcast, Boxed, Story, Social, Hook. Absent leaves the clips uncaptioned. type: string hook_style: description: >- How every hook in the set looks; absent, a white box with dark bold type near the top for three seconds: font_family, font_size (px at the clip's resolution), font_weight (100 to 900), color, background_color (null for none), background_opacity, background_padding, background_radius, position (top-left to bottom-right), offset_y, text_transform (none|uppercase|lowercase|capitalize), animation (none|fade|slide|pop), stroke_color, stroke_width, seconds (0.5 to 15). type: object propertyNames: type: string additionalProperties: {} emphasis: description: The words this set is about, lit and marked. type: object properties: words: description: >- The words drawn in the emphasis color wherever they are spoken. Matched whole and case-insensitively. maxItems: 30 type: array items: type: string color: description: >- What those words are drawn in. Absent takes the look's own accent. type: string emoji: description: >- An emoji written into the line after a word, as {"launch":"🚀"}. Use sparingly: one or two across a clip. type: object propertyNames: type: string additionalProperties: type: string bleep: description: >- Bleep swearing: the sound covered where it is said and the word starred in the captions. true takes the usual list. anyOf: - type: boolean const: true - type: object properties: words: description: >- Words to bleep beyond the usual swearing and slurs, matched whole. maxItems: 50 type: array items: type: string only_these: description: Bleep only the words given. type: boolean with: description: A tone over each word, or silence. Absent is a tone. type: string enum: - tone - silence zoom: description: >- Punch in on the words, as auto_zoom does. Absent leaves the framing still. type: string enum: - light - medium - strong reframe: description: >- Move each clip's crop to follow the subject, for a cut whose shape differs from the recording's. speaker follows whoever is talking where two people share the frame (needs speakers on the recording). anyOf: - type: boolean - type: string const: speaker layout: description: >- For a stream or tutorial with a face-cam: the camera in one band and the screen in the other, each cropped to its region, on tall and square clips. Regions come off a frame (inspect_media). Replaces reframe and zoom. type: object properties: face: type: object properties: x: type: number minimum: 0 maximum: 1 'y': type: number minimum: 0 maximum: 1 w: type: number minimum: 0.03 maximum: 1 h: type: number minimum: 0.03 maximum: 1 required: - x - 'y' - w - h description: Where the camera sits in the recording. screen: description: >- The part of the screen to show. Absent shows the whole picture. type: object properties: x: type: number minimum: 0 maximum: 1 'y': type: number minimum: 0 maximum: 1 w: type: number minimum: 0.03 maximum: 1 h: type: number minimum: 0.03 maximum: 1 required: - x - 'y' - w - h face_share: description: How much of the height the camera takes. Absent is 0.4. type: number minimum: 0.2 maximum: 0.6 face_at: description: Which band the camera takes. Absent is top. type: string enum: - top - bottom required: - face allow_duplicates: description: >- Cut a span the project already holds a clip of. Off, such a span is skipped and the clip it already is named in `skipped`, so a retried call cannot double the set. type: boolean context: description: 'Optional: one sentence shown to the user beside this action.' type: string maxLength: 600 required: - timeline_id - ref - clips 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. ````