# hypit.ai

> Clone any viral video with AI agents. hypit.ai turns a reference video and a prompt into a finished edit — script, timing, tracks and composition — driven from a coding agent or from an OpenAI-shaped API.

The documentation below is written for two audiences. The quickstart is for people directing an agent to produce video; the develop guide is for people extending the toolchain. The API reference covers the generative-media gateway the product runs on: images, video, audio and chat across many upstream vendors behind one key, sold in credits.

## Getting started

- [Quickstart for Agent users](https://hypit.ai/quickstart/): Turn a reference video into a new video for your presenter, product and audience.
- [Script](https://hypit.ai/quickstart/script/): The Script Surface — Segments, Role Cues, Dual Text, Selections, Moments and text projections.
- [SVS Stylesheets](https://hypit.ai/quickstart/styles/): The SVS Recipe language — CSS-like stylesheets for film, caption, media, text and generation settings.
- [Media & Generation](https://hypit.ai/quickstart/generation/): Declaring media assets and generating video with Seedance.
- [Timing & Assembly](https://hypit.ai/quickstart/timing/): Per-take normalization and alignment, followed by SemanticTrack assembly.
- [Tracks](https://hypit.ai/quickstart/tracks/): Peer track components — captions, media, typography and authored audio.
- [Image Operations](https://hypit.ai/quickstart/images/): Compose, correct and cut out images before they reach a generator or a Track.
- [Film & Rendering](https://hypit.ai/quickstart/composition/): Composing tracks into a film and rendering to video.
- [Hypit Studio](https://hypit.ai/quickstart/preview/): Explore a composition, its Sources and Results, and edit its timing and appearance.
- [Run Source & Builds](https://hypit.ai/quickstart/run/): Declaring build targets, reusing results and configuring the runtime.

## Develop

- [Development Guide](https://hypit.ai/guide/develop/): Getting started with Hypit development.
- [Making videos with an Agent](https://hypit.ai/guide/skill/): Give your Agent a reference video or a brief and receive an editable video project.
- [Packages and Extension](https://hypit.ai/guide/packages/): How video projects select components, models and services as ordinary packages.
- [Adding an Author Package](https://hypit.ai/guide/author-packages/): Build a project component, use it in a video, and share it when useful.
- [Component Anatomy](https://hypit.ai/guide/component-anatomy/): Turn a scene's creative interface into a reusable graph contribution.
- [Models and Providers](https://hypit.ai/guide/providers/): Choose an account, connect a service or add a model without changing the video execution system.
- [Runtime](https://hypit.ai/guide/runtime/): The execution boundary outside Hypit source and Core.
- [Studio Companions](https://hypit.ai/guide/studio-companion-architecture/): Give a component useful timeline entities and editing controls in Studio.
- [Studio Temporal Lineage](https://hypit.ai/guide/studio-temporal-windows/): How author choice becomes an Instant or Window and returns to its real source.
- [Testing](https://hypit.ai/guide/testing/): Test runner, patterns and environment-gated tests.
- [Conventions](https://hypit.ai/guide/conventions/): Naming, module boundaries, TypeScript configuration and wire data.

## API reference

- [API overview](https://hypit.ai/api-reference/): One OpenAI-shaped API in front of two dozen generative-media vendors, billed in credits.
- [Authentication](https://hypit.ai/api-reference/authentication/): Create an API key, send it as a bearer token, and read the four failure modes apart.
- [Models](https://hypit.ai/api-reference/models/): List what your key can route to, and read a model's credit rate before you spend anything.
- [Asynchronous jobs](https://hypit.ai/api-reference/jobs/): How image, video and music generation actually works — submit, poll, collect, and what happens to your credits when it fails.
- [Images](https://hypit.ai/api-reference/images/): Generate and edit images. Both endpoints are asynchronous and answer with a job.
- [Video](https://hypit.ai/api-reference/video/): Text to video and image to video. One asynchronous endpoint, priced per second.
- [Audio](https://hypit.ai/api-reference/audio/): Speech synthesis and transcription are synchronous; music generation is a job.
- [Chat completions](https://hypit.ai/api-reference/chat/): The drop-in OpenAI endpoint — synchronous, streaming, vision, tools, vendor passthrough.
- [Gemini native](https://hypit.ai/api-reference/gemini/): Google's own wire format, passed through unchanged — for code already written against the GenAI SDK.
- [Credits and billing](https://hypit.ai/api-reference/billing/): How a call is priced, what a job reserves, and when money comes back.
- [Errors and limits](https://hypit.ai/api-reference/errors/): One error envelope everywhere, what each status means, and the two rate limits that apply.

## About

- [Pricing](https://hypit.ai/commercial/pricing/): Plans, credit packs and how credits are spent
- [Contact](https://hypit.ai/commercial/contact/): Commercial and support enquiries
- [Changelog](https://hypit.ai/changelog/): What shipped, newest first
- [Templates](https://hypit.ai/templates/): Starting points for common video formats
- [Terms of Service](https://hypit.ai/legal/terms/)
- [Privacy Policy](https://hypit.ai/legal/privacy/)