falai

Run Fal.ai image, video, and audio generation models from Robomotion.

2|1|Updated Mar 13, 2026
One-click install
npx skills add https://github.com/robomotionio/robomotion-skills --skill falai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: falai
Source: https://github.com/robomotionio/robomotion-skills/tree/main/skills/falai
Command: npx skills add https://github.com/robomotionio/robomotion-skills --skill falai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Fal.ai models hosted on Fal.ai can require manual setup and orchestration; this Skill wraps Fal.ai in the Robomotion CLI, enabling both synchronous and asynchronous inferences for images, videos, and audio without managing infrastructure.

Core Features & Use Cases

  • Synchronous and asynchronous inference via Fal.ai
  • Connect, submit, poll, and retrieve results using the Robomotion Fal.ai commands
  • Supports image generation, video generation, and text-to-speech tasks
  • Use case: automate media generation pipelines and iterative content creation with AI models hosted on Fal.ai.

Quick Start

Install and configure the Fal.ai integration by connecting a session with robomotion falai falai_connect to obtain a client-id and session-id, then run a model with robomotion falai falai_run_model using those IDs and always append --output json for structured results.

Frequently Asked Questions about falai

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run Fal.ai models for image and video generation from Robomotion?

You can run Fal.ai models by connecting a session with falai_connect to get a client-id and session-id, then executing falai_run_model with those IDs along with the --output json flag for structured results.

What is needed to authenticate Fal.ai cloud inference requests in Robomotion?

Authenticating Fal.ai cloud inference requests requires a Fal.ai account and a configured API key stored in the Robomotion vault. You then use the falai_connect command to establish a session for authorizing inference requests.

Can I use asynchronous inference for text-to-speech tasks via Fal.ai?

Yes, you can use asynchronous inference for text-to-speech tasks via Fal.ai. The integration supports both synchronous and asynchronous workflows, allowing you to submit, poll, and retrieve audio generation results without managing infrastructure.

Does automating media generation pipelines with Fal.ai require managing cloud infrastructure?

No, automating media generation pipelines with Fal.ai does not require managing cloud infrastructure. The Skill wraps Fal.ai in the Robomotion CLI to handle both synchronous and asynchronous inferences seamlessly.

What are the steps to retrieve results from a Fal.ai asynchronous inference job?

To retrieve results from a Fal.ai asynchronous inference job, you submit the task using falai_run_model, poll the session for completion, and retrieve the final generated media output by appending --output json to your commands.