SISIF
REST API for programmatic text-to-video generation, optimized for short vertical social clips.
Pick SISIF if you need to wire text-to-video into a backend or n8n workflow for short vertical social clips without a subscription commitment.
Skip it if you need horizontal/cinematic video, transparent model provenance, or high-volume guaranteed throughput.
SISIF is a developer-facing text-to-video API that turns text prompts into short vertical videos in roughly 2-5 minutes. It exposes a simple REST endpoint with bearer-token auth, a polling status route, and webhook callbacks, plus a built-in n8n integration for non-code workflow automation. Output is fixed to vertical aspect ratios at 540x960 or 720x1280, clearly aimed at TikTok, Reels, and Shorts pipelines rather than cinematic horizontal video.
Pricing is credit-based with no subscription: 4 credits/sec at the high tier and 6 credits/sec at the ultra tier, with 35 free credits on signup and no card required. That makes it a reasonable pick for solo creators, marketers, and small automation shops who want to wire generative video into their existing stack without negotiating with enterprise sales. Rate limits (10/min, 100/hour, 1000/day by default) are generous enough to script but signal this is a shared API, not a dedicated GPU lease.
The page does not disclose the underlying model, which is the main caveat: you can't independently judge quality, motion fidelity, or prompt adherence without burning credits. There is also no public showcase of motion-heavy benchmarks, and the lack of horizontal output rules out broader use cases. For teams who just need to drop programmatic short-form video into an n8n or backend workflow, the API surface is refreshingly minimal.
A pragmatic, API-first video generator that gets out of the way: credits, a REST call, webhooks, done. The hard-coded vertical formats and undisclosed model mean you should spend the free 35 credits before committing, but as a glue component for automated short-form pipelines it fills a niche the big labs ignore.
— The AI Tool Bible editorial team
Pros
- ✅ Clean REST API with bearer auth, polling, and webhooks
- ✅ Native n8n integration for no-code workflow chaining
- ✅ Pay-as-you-go credits with a free tier and no card required
- ✅ Commercial rights to generated videos included
Cons
- ⚠️ Underlying model is undisclosed, so quality is unknown until tested
- ⚠️ Vertical-only output (540x960 / 720x1280); no horizontal formats
- ⚠️ Default rate limits constrain bulk generation workloads
Use cases
Explore related
Compare with similar tools
All in Video →Runway
FeaturedPro-grade AI video editor and Gen-4 generation.
Sora
FeaturedOpenAI's flagship text-to-video model.
Luma Dream Machine
Fast, accessible text-to-video with strong camera control.
HeyGen
Avatar video + lip-sync translation at scale.
Synthesia
Enterprise AI avatar video creator for L&D and product marketing.
Kling
Kuaishou's Sora competitor — strong on motion fidelity.