​

Text-to-Video Generation

The Text-to-Video node generates video clips directly from text descriptions. Choose from 12 AI video generation engines with varying quality, speed, and cost. The default is Kling 3.0.

​

Inputs

​

Outputs

​

Available engines

​

Configuration options

​

Advanced options

​

Credit cost

Cost = per-second rate x duration. Default duration is 5 seconds. See Model Costs for detailed pricing.

​

Tips

• Veo 3.1 Lite is the cheapest option at 15 credits for a 5s clip @ 720p
• Kling 3.0 (default) is a strong balance of quality and price
• Seedance 2.0 and Veo 3.1 are the highest-quality options
• Seedance 2.0, Veo 3.1, and Wan 2.7 generate native audio with the video
• Veo 3.1 supports up to 4K resolution
• Videos are generated at 9:16 aspect ratio (vertical/portrait)

​

Example use cases

• Generating scene clips from script descriptions
• Creating B-roll footage from text descriptions
• Producing animated backgrounds or environments