Varosity Documentation
Varosity is one MCP server and API for 70+ video, image, voice and music models, built to be called by AI agents. Start with whichever door fits.
Connect an agent
Your agent connects itself; you approve once and set a daily limit.
MCP tools & agent guide
Every tool, the job/poll shape, and tips for agents.
REST API
Plain HTTP with an OpenAPI spec, plus llms.txt for agents.
Guides
5-minute first render
Your first AI video in five minutes: describe it, pick one of three frames, get a clip. Runs on Varosity credits, so no provider keys are needed.
beginner · 5 min
Agent mode (Claude / Cursor / MCP)
Drive Varosity from any MCP host: 46 tools (29 for apps that sign in with OAuth), bearer auth, JSON-RPC over Streamable HTTP.
intermediate · 7 min
Avatar on any background
Put an OmniHuman talking-head avatar over a background clip from Kling, Runway or another model, picture-in-picture, in one render.
intermediate · 8 min
Background music
Generate a soundtrack with ElevenLabs Music, Lyria or Suno and lay it under your video with the stitch step. Auto-ducking under speech is not available yet.
beginner · 5 min
BYOK setup per provider
Where to get an API key for fal.ai, Replicate, ElevenLabs, OpenAI, Google, Fish Audio and Cartesia, and how to add, test and rotate it in Varosity.
beginner · 5 min
Call the Varosity API from Python
Generate video from any Python agent with plain requests: submit a job, poll it, download the MP4. One API key, no SDK to install.
intermediate · 10 min
Chaining clips across models
Pick the right model for each shot — dialogue, action, b-roll — then stitch the clips into one MP4 with Varosity's stitch step.
beginner · 10 min
Director Mode
Plan, visualise, and approve video campaigns before a single frame renders.
intermediate · 8 min
Managing renders + costs
Where renders live, how long provider video links last, how to download them, and how to keep spend under control with caps and your own keys.
beginner · 4 min
Multi-shot consistency with locked references
Enforce visual continuity across multi-shot video sequences. Lock one reference image, vary model and prompt per shot.
intermediate · 8 min
Picking the right model
Strengths and weaknesses cheat sheet across every video, voice, and music model.
beginner · 4 min
Prompting cheatsheet
Camera moves, lighting and motion phrases that work the same way across Kling, Veo, Seedance, Runway and other video models, with examples.
intermediate · 6 min
Provider options (advanced knobs)
Every per-model providerOptions field across image, video, and voice — exact names, allowed values, and examples.
advanced · 7 min
Save as workflow template
Save a project as a reusable workflow; start new projects from it or from a curated template (UI, CLI, MCP).
intermediate · 5 min
Using the CLI
Install @varosity/cli, pair it with your account, and render videos and music from the terminal or a script.
intermediate · 6 min
Voice over your video
Add narration to a video with ElevenLabs, OpenAI TTS, Deepgram, Cartesia or Fish Audio: pick a voice, generate the line, and mix it into the final cut.
beginner · 6 min