Generate AI videos from text prompts using multiple provider gateways. Use when: (1) Generating videos from text descriptions, (2) Creating AI-generated video clips for content production, (3) Image-to-video generation with a reference image, (4) Choosing between video generation providers (VEO, Kli

Video Generation (Multi Gateway) Generate AI videos from text prompts. Supports multiple providers via two API gateways: Gateway Env Variable Providers Tool fal.ai FAL KEY Seedance 2.0 (standard + fast), Kling v3/v2.1, MiniMax, VEO seedance video , kling video , minimax video , veo video HeyGen HEYGEN API KEY VEO 3.1, Kling Pro, Sora v2, Runway Gen 4, Seedance Pro / Lite (1.x) heygen video Gemini API GEMINI API KEY / GOOGLE API KEY Gemini Omni Flash (generation + conversational editing) gemini omni video Iterative editing — Gemini Omni. When the brief calls for refining an existing clip (add/remove objects, restyle, change lighting or on screen text) rather than regenerating, Gemini Omni Flash is the only provider in the fleet with stateful multi turn editing. See Layer 3 gemini omni for the authoritative prompting guide (reference image tags, timecode syntax, edit prompt rules) before writing any prompt for it. Preferred premium default — Seedance 2.0. When any premium gateway is configured ( FAL KEY → seedance video , or HeyGen's Video Agent / Avatar Shots path), Seedance 2.0 is the preferred default for cinematic, trailer, and high fidelity clip work. It is the only model in the fleet with single pass native synchronized audio, multi shot generation, director level camera control, and lip sync from quoted dialogue , and it ranks 1 on Artificial Analysis Elo as of early 2026. Switch off it only when the user has a specific reason (budget, provider preference, stylistic fit like VEO for photoreal landscape or Kling for specific anime look). See Layer 3 seedance 2 0 for the authoritative prompting and parameter guide. IMPORTANT: Always use video selector instead of calling provider tools directly. The selector handles availability checks, cost comparison, and automatic fallback, and its scoring engine already biases toward Seedance 2.0 for cinematic intent. Authentication Use whichever configured gateway best matches the user's available providers and cost/quality goals. HeyGen: Set HEYGEN API KEY to access the multi model gateway. fal.ai: Set FAL KEY to access Kling, MiniMax, and Veo through fal.ai. Do not describe either gateway as the default or top choice without checking the registry and current task fit first. Default Workflow 1. Call POST /v1/workflows/executions with workflow type: "GenerateVideoNode" and your prompt 2. Receive a execution id in the response 3. Poll GET /v1/workflows/executions/{id} every 10 seconds until status is completed 4. Use the returned video url from the output Execute Video Generation Endpoint POST https://api.heygen.com/v1/workflows/executions Request Fields Field Type Req Description : : workflow type string Y Must be "GenerateVideoNode" input.prompt string Y Text description of the video to generate input.provider string Video generation provider (default: "veo 3 1" ). See Providers below. input.aspect ratio string Aspect ratio (default: "16:9" ). Common values: "16:9" , "9:16" , "1:1" input.reference image url string Reference image URL for image to video generation input.tail image url string Tail image URL for last frame guidance input.config object Provider specific configuration overrides Providers Provider Value Description VEO 3.1 "veo 3 1" Google VEO 3.1 (default, highest quality) VEO 3.1 Fast "veo 3 1 fast" Faster VEO 3.1 variant VEO 3 "veo3" Google VEO 3 VEO 3 Fast "veo3 fast" Faster VEO 3 variant VEO 2 "veo2" Google VEO 2 Kling Pro "kling pro" Kling Pro model Kling V2 "kling v2" Kling V2 model Sora V2 "sora v2" OpenAI Sora V2 Sora V2 Pro "sora v2 pro" OpenAI Sora V2 Pro Runway Gen 4 "runway gen4" Runway Gen 4 Seedance Lite "seedance lite" Seedance Lite Seedance Pro "seedance pro" Seedance Pro LTX Distilled "ltx distilled" LTX Distilled (fastest) curl TypeScript Python Response Format Check Status Endpoint GET https://api.heygen.com/v1/workflows/executions/{execution id} curl Response Format (Completed) Polling for Completion Usage Examples Simple Text to Video Image to Video Vertical Format for Social Media Fast Generation with LTX Best Practices 1. Be descriptive in prompts — include camera movement, lighting, style, and mood details 2. Default to Seedance 2.0 (via seedance video ) for cinematic and motion led work when FAL KEY is set — single pass synced audio, multi shot, lip sync, director level camera. Use VEO 3.1 / Sora V2 Pro when the user specifically wants Google or OpenAI motion character; use ltx distilled or veo3 fast only when speed is the hard constraint 3. Use reference images for image to video generation — great for animating product photos or still images 4. Video generation is the slowest workflow — allow up to 5 minutes, poll every 10 seconds 5. Aspect ratio matters — use 9:16 for social media stories/reels, 16:9 for landscape, 1:1 for square 6. Output includes asset id — use this to reference the generated video in other HeyGen workflows 7. Output URLs are temporary — download or save generated videos promptly

ai-video-gen