Skip to content

Quick Start

This guide will help you install Renku, set up your workspace, configure API keys, and generate your first AI-powered video.

Before installing Renku, ensure you have:

  • Node.js 18+ - Download from nodejs.org
  • pnpm - Install with npm install -g pnpm

Install the Renku CLI globally:

Terminal window
npm install -g @renku/cli

Verify the installation:

Terminal window
renku --version

Initialize a new Renku workspace:

Terminal window
renku init --root-folder=/path/to/your/workspace

For example:

Terminal window
renku init --root-folder=~/renku-projects

This creates:

  • ~/.config/renku/cli-config.json - Configuration file
  • {workspace}/builds/ - Directory for generated movie outputs
  • {workspace}/catalog/blueprints/ - Bundled blueprint templates

Renku uses multiple AI providers. You’ll need API keys for the providers used by your chosen blueprint.

Most blueprints require:

ProviderPurposeGet API Key
OpenAIScript generation, prompt creationplatform.openai.com
ReplicateVideo, audio, image generationreplicate.com

Optional providers:

  • fal.ai - Alternative video/image models
  • ElevenLabs - High-quality voice synthesis

Create a .env file in your workspace or export variables directly:

Terminal window
# Required
export OPENAI_API_KEY=sk-...
export REPLICATE_API_TOKEN=r8_...
# Optional
export FAL_KEY=...
export ELEVENLABS_API_KEY=...

List available blueprints:

Terminal window
renku blueprints:list

For this tutorial, we’ll use the audio-only blueprint which generates narrated audio segments.

Each blueprint has an input template. Copy it to create your inputs file:

Terminal window
cp {workspace}/catalog/blueprints/audio-only/input-template.yaml ./my-inputs.yaml

Edit my-inputs.yaml with your content:

inputs:
InquiryPrompt: "Explain the water cycle for middle school students"
Duration: 60
NumOfSegments: 3
VoiceId: "Wise_Woman"
Emotion: "neutral"

Before using real API credits, validate your setup with a dry run:

Terminal window
renku generate \
--inputs=./my-inputs.yaml \
--blueprint={workspace}/catalog/blueprints/audio-only/audio-only.yaml \
--dry-run

The dry run:

  • Validates your blueprint and inputs
  • Shows the execution plan
  • Creates mock artifacts (no API calls)

When you’re ready, run the full generation:

Terminal window
renku generate \
--inputs=./my-inputs.yaml \
--blueprint={workspace}/catalog/blueprints/audio-only/audio-only.yaml

Watch as Renku:

  1. Generates a narration script using OpenAI
  2. Creates audio for each segment using your chosen voice
  3. Saves all artifacts to the build directory

Open the generated content in the viewer:

Terminal window
renku viewer:view --last

This starts a local viewer server and opens your browser to preview the generated content.

After generation, your workspace contains:

{workspace}/
├── builds/
│ └── movie-{id}/
│ ├── blobs/ # Generated files (audio, images, etc.)
│ ├── manifests/ # Artifact metadata
│ ├── events/ # Execution logs
│ └── runs/ # Execution plans
└── movies/
└── movie-{id}/ # Friendly view with symlinks
├── Script.txt # Generated narration script
├── Segment_0.mp3 # Audio for segment 0
├── Segment_1.mp3 # Audio for segment 1
└── Segment_2.mp3 # Audio for segment 2

The movies/ directory contains human-readable symlinks to your generated content.

You’ve successfully generated your first AI video content with Renku!

Try other bundled blueprints:

Terminal window
renku blueprints:list
renku blueprints:describe {workspace}/catalog/blueprints/video-only/video-only.yaml

Read the Usage Guide to learn:

  • How to edit and iterate on generated content
  • Using layer-by-layer generation for cost control
  • Browsing available models and producers

For advanced users:

Error: OPENAI_API_KEY not found

Solution: Export your API key or add it to a .env file in your workspace.

Error: Blueprint file not found

Solution: Use the full path to the blueprint file. After renku init, blueprints are in {workspace}/catalog/blueprints/.

If you hit rate limits, wait a few minutes and try again. Consider using --up-to-layer to generate in stages.

Check that:

  1. All required API keys are set
  2. Your API accounts have sufficient credits
  3. The model names in the inputs file are valid

Run renku producers:list --blueprint=<path> to see available models and check for missing tokens.