Skip to content

Quickstart

Generate your first video in under a minute.

1. Install

pip install tarash-gateway[fal]

2. Generate a video

from tarash.tarash_gateway import generate_video
from tarash.tarash_gateway.models import VideoGenerationConfig, VideoGenerationRequest

config = VideoGenerationConfig(
    provider="fal",
    api_key="YOUR_FAL_API_KEY",
    model="fal-ai/veo3.1/fast",
)

request = VideoGenerationRequest(
    prompt="A golden retriever running on a beach at sunset, cinematic slow motion",
    duration_seconds=4,
    aspect_ratio="16:9",
)

response = generate_video(config, request)
print(response.video)

3. Generate an image

from tarash.tarash_gateway import generate_image
from tarash.tarash_gateway.models import ImageGenerationConfig, ImageGenerationRequest

config = ImageGenerationConfig(
    provider="fal",
    api_key="YOUR_FAL_API_KEY",
    model="fal-ai/flux/dev",
)

request = ImageGenerationRequest(
    prompt="A futuristic cityscape at dawn, neon lights reflecting on wet streets",
    size="1024x1024",
)

response = generate_image(config, request)
print(response.images)

4. Generate asynchronously

import asyncio
from tarash.tarash_gateway import generate_video_async
from tarash.tarash_gateway.models import VideoGenerationConfig, VideoGenerationRequest

async def main():
    config = VideoGenerationConfig(provider="fal", api_key="YOUR_KEY")
    request = VideoGenerationRequest(prompt="A timelapse of a blooming flower")

    response = await generate_video_async(config, request)
    print(response.video)

asyncio.run(main())

5. Track progress

from tarash.tarash_gateway.models import VideoGenerationUpdate

def on_progress(update: VideoGenerationUpdate) -> None:
    print(f"Status: {update.status} — {update.progress_percent}%")

response = generate_video(config, request, on_progress=on_progress)

Next steps