Text to Video
Generate videos from text descriptions. Describe a scene or action and these models will create a video based on your prompt.
Seedance 2.5
variable creditsNative 30-second cinematic video from text with synchronized audio in a single pass.
FLUX 3
variable creditsBlack Forest Labs frontier video with native audio, up to 20 seconds at 1080p.
Kling O3 Pro
variable creditsKling O3 Pro text-to-video with native audio and multi-shot generation. Use prompt or multi_prompt, not both.
Grok Imagine Video 1.5
variable creditsxAI video with native audio, 1–15 seconds, up to 1080p.
Seedance 2.0
variable creditsGenerate cinematic video from text with native synchronized audio (SFX, ambient, lip-synced speech) at no extra cost.
OpenAI Sora 2
20 creditsBest video generation model available can produce video with sound in 720p.
OpenAI Sora 2 Pro
60 creditsCan produce up to 1080p videos with sound and music. Very good quality.
Google Veo 3.1 Fast
variable creditsKling Video v3 Standard
variable creditsHigh-quality text-to-video with native audio generation. Supports multi-shot generation. Use either prompt OR multi_prompt, not both. Keep prompts short.
Kling Video v3 Pro
variable creditsHigh-quality text-to-video with native audio generation. Supports multi-shot generation. Use either prompt OR multi_prompt, not both. Keep prompts short.
Happy Horse 1.1
variable credits1080p text-to-video with synchronized audio and multilingual lip-sync.
MiniMax H3
variable creditsFrontier 2K text-to-video with native stereo audio, 5–15 seconds.