Slicer API for developers
Video editing API: vertical videos straight from your code
The Slicer REST API does what the app does: it takes video, photos and audio, assembles the video with editor operations or runs AI editing, and exports a finished file. A project without the AI director and all edits are free; AI editing and AI features show their price before the run.
- First project free
- No card needed
- Ready in minutes
Editing as a service — one request from your system
REST and OpenAPI 3.1
JSON, a Bearer token and an open spec with no sign-in — generate a client for your language.
Price before the run
A paid operation without confirmCost only returns the price: AI editing and AI features start with the confirmed amount.
Four ways to upload
A one-time link for curl -T, a whole file, resumable parts or import from a public address.
74 edit operations
Word-level editing, cutting, color, elements, music, voice, inserts — the same operations as the editor.
Signed webhooks
project.succeeded, export.succeeded, publication.published — HMAC signatures and delivery retries.
Tokens that fit the job
Access scopes, an expiry from 30 days to never, and a monthly spend limit on every token.
How it works
How to make your first video with the API
- 1
Create a token
Profile → For developers in the app: the Montage set, an expiry and a spend limit.
- 2
Upload and get a price
POST /v1/uploads, then POST /v1/projects without confirmCost — the response is a price, nothing runs.
- 3
Run it and get the video
The same request with confirmCost, a webhook when it’s ready and the file at GET /v1/projects/{id}/result.
Documentation
The Slicer API in the docs
A quickstart in curl, JavaScript and Python, tokens and scopes, uploads, editing and pricing, edits, export, webhooks and a reference for every endpoint.
Automated video editing through an API
The Slicer API fits when you have many videos or they originate in your own system: a webinar recording, an interview from your CRM, a product video from your catalog. Your code uploads the media and starts the edit, and Slicer’s team of neural networks does the rest: it transcribes speech word by word, understands what is in the frame and builds a vertical video with captions, push-ins and sound, which the director reviews before handing it over.
Every response uses the same { ok, data } shape, and errors come with clear codes. Retrying after a network failure is safe: the Idempotency-Key header prevents a double run.
Edits through editor operations
Slicer has one catalog of operations: manual edits in the editor, the AI assistant and the director in the chat all apply the same ones. So a change your code makes through the API looks exactly like an edit in the app. Edits themselves are free.
- word-level editing: cut filler words, restore a line, add a hook
- cutting: split, trim and reorder fragments
- color, effects, transitions, speed and volume
- captions, callouts, titles, emoji and push-ins
- music, voice and inserts over the video
- captions from speech, the one-command AI assistant and caption translation — at cost
Export, publishing and notifications
Export re-renders the video with your file settings and can publish it to connected social accounts. Webhooks tell you when it’s ready: the HMAC signature proves the request came from Slicer, and delivery is retried if your server didn’t answer.
For AI agents there is an MCP server with the same capabilities and no code. Recipes in the docs cover typical jobs: a video from a folder in Node.js, batch processing in Python and notifications via a webhook.
AI director
A director that checks its own work
Once the reel is built, the director watches it start to finish — in viewing order, with what is on screen and what the viewer hears. It fixes the order, the logic and cut-off thoughts, and if the plan changes, it rebuilds the reel. You get one finished reel — already checked.
Tell the director what kind of reel you need
Notes for the director
Open with the most striking moment, make it punchier and end with a call to subscribe
Pricing
Pay for reels, not a subscription
The in-app currency is tokens. A reel up to 90 seconds costs 24 tokens: it includes a finished reel checked by the director, editor tweaks and export.
Free start
0 ₽
- 1 project
- A full AI edit, checked by the director
- “Slicer” watermark
- Buy any pack — we re-render it without the watermark for free
Edits, color, on-device rendering and export are free. AI operations in the editor are at cost, with the price shown before you start. If an edit fails, tokens come back automatically.
Questions and answers
How much does editing through the API cost?
A project without the AI director, edits, version choice, style changes and export are free. AI editing costs the same as in the app: 24 tokens per video, from 129 ₽ in a large pack. Captions from speech, the AI assistant and translation are at cost.
How do I avoid overspending?
A paid operation without confirmCost only returns the price. Each token also has a monthly spend limit, and without the montage:run scope it can’t spend a single token.
What files can I upload?
Video, photos and audio — the same formats as in the app. Large files are easiest to upload in parts, and Slicer downloads a file from a public https address by itself.
How do I know the video is ready?
Poll the project every few seconds or subscribe to webhooks: project.succeeded, project.version_ready, export.succeeded and more.
Is there a spec to generate a client?
Yes: OpenAPI 3.1 at https://api.slicer.media/v1/openapi.json, no sign-in needed. The reference in the docs is built from it.
Can I build a video without the AI director?
Yes: a project without the AI director is free — media goes onto the timeline and you assemble the video with edit operations.
Your first reel is free
Sign up in a minute. No card needed.
- First project free
- No card needed
- Ready in minutes