Happy Horse 1.0 is now on fal
Docs
Log-inSign-up

fal-ai/marlin

Marlin is a 2B video VLM tuned for the two questions developers actually want to ask of their videos: what is happening, and when?
Inference
Commercial use
Schema
LLMs
PlaygroundAPIExamples

Table of contents

About

Caption

1. Calling the API#

Install the client#

The client provides a convenient way to interact with the model API.

npm install --save @fal-ai/client

Setup your API Key#

Set FAL_KEY as an environment variable in your runtime.

export FAL_KEY="YOUR_API_KEY"

Submit a request#

The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/marlin", {
  input: {
    video_url: "https://v3b.fal.media/files/b/0a913346/ZbEaRKcU1dMNYkHl9g1Zz_T4QEyOJ3R3WzuQS9.mp4",
    prompt: "Provide a spatial description of this clip followed by time-ranged events.
  For each event, give the time range as <start - end> and a short description."
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

2. Authentication#

The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.

API Key#

In case your app is running in an environment where you cannot set environment variables, you can set the API Key manually as a client configuration.
import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

3. Queue#

Submit a request#

The client API provides a convenient way to submit requests to the model.

import { fal } from "@fal-ai/client";

const { request_id } = await fal.queue.submit("fal-ai/marlin", {
  input: {
    video_url: "https://v3b.fal.media/files/b/0a913346/ZbEaRKcU1dMNYkHl9g1Zz_T4QEyOJ3R3WzuQS9.mp4",
    prompt: "Provide a spatial description of this clip followed by time-ranged events.
  For each event, give the time range as <start - end> and a short description."
  },
  webhookUrl: "https://optional.webhook.url/for/results",
});

Fetch request status#

You can fetch the status of a request to check if it is completed or still in progress.

import { fal } from "@fal-ai/client";

const status = await fal.queue.status("fal-ai/marlin", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
  logs: true,
});

Get the result#

Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.

import { fal } from "@fal-ai/client";

const result = await fal.queue.result("fal-ai/marlin", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);

4. Files#

Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.

Data URI (base64)#

You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.

Hosted files (URL)#

You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.

Uploading files#

We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.

import { fal } from "@fal-ai/client";

const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);

Read more about file handling in our file upload guide.

5. Schema#

Input#

video_url string* required

URL of the video to caption. Up to ~2 minutes is supported.

prompt string* required

Caption prompt sent to the model. The example value is Marlin's canonical training prompt — overriding usually degrades output quality.

max_tokens integer

Maximum number of tokens to generate for the caption. Default value: 2048

do_sample boolean

If true, sample with temperature/top_p; if false, use greedy decoding.

temperature float

Sampling temperature. Only used when do_sample is true. Default value: 1

top_p float

Nucleus sampling threshold. Only used when do_sample is true. Default value: 1

{
  "video_url": "https://v3b.fal.media/files/b/0a913346/ZbEaRKcU1dMNYkHl9g1Zz_T4QEyOJ3R3WzuQS9.mp4",
  "prompt": "Provide a spatial description of this clip followed by time-ranged events.\nFor each event, give the time range as <start - end> and a short description.",
  "max_tokens": 2048,
  "temperature": 1,
  "top_p": 1
}

Output#

scene string* required

Spatial description of the clip.

events list<EventSegment>* required

Time-ranged events parsed from the caption.

text string* required

Full post-thinking caption text (Scene + Events) as returned by the model.

{
  "scene": "",
  "events": [
    {
      "start": 0,
      "text": "a person waves",
      "end": 1.5
    }
  ],
  "text": ""
}

Other types#

EventSegment#

start float* required

Start time in seconds.

end float* required

End time in seconds.

text string

Short description of the event (caption mode only).