# AI video generation API 93 tools from fal.ai, from $0.002 per second. ## Capabilities - [Seedance](/tools/video-generation/seedance.md): 7 tools. - [Kling](/tools/video-generation/kling.md): 6 tools, from $0.112 per second. - [Veo 3.1](/tools/video-generation/veo.md): 4 tools. - [Gemini Omni](/tools/video-generation/gemini-omni.md): 3 tools. - [MiniMax Hailuo](/tools/video-generation/minimax.md): 20 tools, from $0.002 per second. - [Wan](/tools/video-generation/wan.md): 1 tool. - [LTX](/tools/video-generation/ltx.md): 2 tools. - [Luma Ray](/tools/video-generation/luma-ray.md): 2 tools, from $0.03 per second. - [PixVerse](/tools/video-generation/pixverse.md): 2 tools. - [Grok Imagine Video](/tools/video-generation/grok-imagine-video.md): 5 tools. - [Vidu](/tools/video-generation/vidu.md): 2 tools. - [Talking avatar (OmniHuman)](/tools/video-generation/talking-avatar.md): 1 tool. - [Lip sync](/tools/video-generation/lip-sync.md): 5 tools, from $0.07 per unit. ## All 93 tools - [Seedance 2.5 draft completion](/providers/fal/bytedance-seedance-2-5-draft-complete.md): `fal/bytedance-seedance-2-5-draft-complete`, usage based, the maximum is shown before a run. Needs draft id. Served by fal.ai. - [Seedance 2.5 image to video](/providers/fal/seedance-2-5-image-to-video.md): `fal/seedance-2-5-image-to-video`, usage based, the maximum is shown before a run. Needs image url. Served by fal.ai. - [Seedance 2.5 reference images and audio to video](/providers/fal/seedance-2-5-reference-to-video.md): `fal/seedance-2-5-reference-to-video`, usage based, the maximum is shown before a run. Takes generate audio, codec, draft and more, all optional. Served by fal.ai. - [Seedance 2.5 text to video](/providers/fal/seedance-2-5-text-to-video.md): `fal/seedance-2-5-text-to-video`, usage based, the maximum is shown before a run. Needs prompt. Served by fal.ai. - [Seedance 2.5 US image to video](/providers/fal/bytedance-seedance-2-5-us-image-to-video.md): `fal/bytedance-seedance-2-5-us-image-to-video`, usage based, the maximum is shown before a run. Needs image url. Served by fal.ai. - [Seedance 2.5 US reference to video](/providers/fal/bytedance-seedance-2-5-us-reference-to-video.md): `fal/bytedance-seedance-2-5-us-reference-to-video`, usage based, the maximum is shown before a run. Takes image urls, codec, prompt and more, all optional. Served by fal.ai. - [Seedance 2.5 US text to video](/providers/fal/bytedance-seedance-2-5-us-text-to-video.md): `fal/bytedance-seedance-2-5-us-text-to-video`, usage based, the maximum is shown before a run. Needs prompt. Served by fal.ai. - [Kling 3.0 Pro image to video](/providers/fal/kling-v3-pro-image-to-video.md): `fal/kling-v3-pro-image-to-video`, from $0.112 per second. Needs start image url. Served by fal.ai. - [Kling 3.0 Pro text to video](/providers/fal/kling-v3-pro-text-to-video.md): `fal/kling-v3-pro-text-to-video`, from $0.112 per second. Takes shot type, multi prompt, aspect ratio and more, all optional. Served by fal.ai. - [Kling O3 4K image to video](/providers/fal/kling-o3-4k-image-to-video.md): `fal/kling-o3-4k-image-to-video`, $0.42 per second. Needs image url. Served by fal.ai. - [Kling O3 4K text to video](/providers/fal/kling-o3-4k-text-to-video.md): `fal/kling-o3-4k-text-to-video`, $0.42 per second. Takes prompt, shot type, multi prompt and more, all optional. Served by fal.ai. - [Kling O3 Pro image to video](/providers/fal/kling-o3-pro-image-to-video.md): `fal/kling-o3-pro-image-to-video`, from $0.112 per second. Needs image url. Served by fal.ai. - [Kling O3 Pro text to video](/providers/fal/kling-o3-pro-text-to-video.md): `fal/kling-o3-pro-text-to-video`, from $0.112 per second. Takes prompt, shot type, multi prompt and more, all optional. Served by fal.ai. - [Veo 3.1 Fast image to video](/providers/fal/veo-3-1-fast-image-to-video.md): `fal/veo-3-1-fast-image-to-video`, usage based, the maximum is shown before a run. Needs prompt and image url. Served by fal.ai. - [Veo 3.1 Fast text to video](/providers/fal/veo-3-1-fast-text-to-video.md): `fal/veo-3-1-fast-text-to-video`, usage based, the maximum is shown before a run. Needs prompt. Served by fal.ai. - [Veo 3.1 image to video](/providers/fal/veo-3-1-image-to-video.md): `fal/veo-3-1-image-to-video`, usage based, the maximum is shown before a run. Needs prompt and image url. Served by fal.ai. - [Veo 3.1 text to video](/providers/fal/veo-3-1-text-to-video.md): `fal/veo-3-1-text-to-video`, usage based, the maximum is shown before a run. Needs prompt. Served by fal.ai. - [Gemini Omni Flash 1.1 image to video](/providers/fal/gemini-omni-flash-image-to-video.md): `fal/gemini-omni-flash-image-to-video`, usage based, the maximum is shown before a run. Needs prompt and image url. Served by fal.ai. - [Gemini Omni Flash 1.1 text to video](/providers/fal/gemini-omni-flash-text-to-video.md): `fal/gemini-omni-flash-text-to-video`, usage based, the maximum is shown before a run. Needs prompt. Served by fal.ai. - [Gemini Omni Flash 1.1 video edit](/providers/fal/gemini-omni-flash-video-edit.md): `fal/gemini-omni-flash-video-edit`, usage based, the maximum is shown before a run. Needs prompt and video url. Served by fal.ai. - [MiniMax H3 Max 16-bit pixel styles](/providers/fal/minimax-h3-max-styles-16bit-pixel.md): `fal/minimax-h3-max-styles-16bit-pixel`, $0.08 per second. Needs prompt. Served by fal.ai. - [MiniMax H3 Max 3D to video](/providers/fal/minimax-h3-max-3d-to-video.md): `fal/minimax-h3-max-3d-to-video`, usage based, the maximum is shown before a run. Needs video url. Served by fal.ai. - [MiniMax H3 Max camera controls](/providers/fal/minimax-h3-max-camera-controls.md): `fal/minimax-h3-max-camera-controls`, usage based, the maximum is shown before a run. Needs image url and prompt expansion mode. Served by fal.ai. - [MiniMax H3 Max extend video](/providers/fal/minimax-h3-max-extend-video.md): `fal/minimax-h3-max-extend-video`, usage based, the maximum is shown before a run. Needs video url and prompt. Served by fal.ai. - [MiniMax H3 Max hand drawn styles](/providers/fal/minimax-h3-max-styles-hand-drawn.md): `fal/minimax-h3-max-styles-hand-drawn`, $0.08 per second. Needs prompt. Served by fal.ai. - [MiniMax H3 Max image to video](/providers/fal/minimax-h3-max-image-to-video.md): `fal/minimax-h3-max-image-to-video`, usage based, the maximum is shown before a run. Needs prompt and prompt expansion mode. Served by fal.ai. - [MiniMax H3 Max insert video](/providers/fal/minimax-h3-max-insert-video.md): `fal/minimax-h3-max-insert-video`, usage based, the maximum is shown before a run. Needs video url, start time and resume time. Served by fal.ai. - [MiniMax H3 Max lip sync image to video](/providers/fal/minimax-h3-max-lip-sync-image-to-video.md): `fal/minimax-h3-max-lip-sync-image-to-video`, usage based, the maximum is shown before a run. Needs image url and audio url. Served by fal.ai. - [MiniMax H3 Max low poly styles](/providers/fal/minimax-h3-max-styles-low-poly.md): `fal/minimax-h3-max-styles-low-poly`, $0.08 per second. Needs prompt. Served by fal.ai. - [MiniMax H3 Max recast](/providers/fal/minimax-h3-max-recast.md): `fal/minimax-h3-max-recast`, usage based, the maximum is shown before a run. Needs video url and reference image urls. Served by fal.ai. - [MiniMax H3 Max reference to video](/providers/fal/minimax-h3-max-reference-to-video.md): `fal/minimax-h3-max-reference-to-video`, usage based, the maximum is shown before a run. Needs prompt and prompt expansion mode. Served by fal.ai. - [MiniMax H3 Max retro toon 70s styles](/providers/fal/minimax-h3-max-styles-retro-toon-70s.md): `fal/minimax-h3-max-styles-retro-toon-70s`, $0.08 per second. Needs prompt. Served by fal.ai. - [MiniMax H3 Max text to video](/providers/fal/minimax-h3-max-text-to-video.md): `fal/minimax-h3-max-text-to-video`, usage based, the maximum is shown before a run. Needs prompt and prompt expansion mode. Served by fal.ai. - [MiniMax H3 Max Turbo extend video](/providers/fal/minimax-h3-max-turbo-extend-video.md): `fal/minimax-h3-max-turbo-extend-video`, usage based, the maximum is shown before a run. Needs video url and prompt. Served by fal.ai. - [MiniMax H3 Max Turbo image to video](/providers/fal/minimax-h3-max-turbo-image-to-video.md): `fal/minimax-h3-max-turbo-image-to-video`, usage based, the maximum is shown before a run. Needs prompt and prompt expansion mode. Served by fal.ai. - [MiniMax H3 Max Turbo text to video](/providers/fal/minimax-h3-max-turbo-text-to-video.md): `fal/minimax-h3-max-turbo-text-to-video`, usage based, the maximum is shown before a run. Needs prompt and prompt expansion mode. Served by fal.ai. - [MiniMax H3 Max VHS styles](/providers/fal/minimax-h3-max-styles-vhs.md): `fal/minimax-h3-max-styles-vhs`, $0.08 per second. Needs prompt. Served by fal.ai. - [MiniMax Music 3](/providers/fal/minimax-music-3.md): `fal/minimax-music-3`, $0.002 per second. Needs prompt and lyrics. Served by fal.ai. - [MiniMax Speech 2.8 HD](/providers/fal/minimax-speech-2-8-hd.md): `fal/minimax-speech-2-8-hd`, $0.1 per 1,000 characters. Needs prompt. Served by fal.ai. - [MiniMax Speech 2.8 Turbo](/providers/fal/minimax-speech-2-8-turbo.md): `fal/minimax-speech-2-8-turbo`, $0.06 per 1,000 characters. Needs prompt. Served by fal.ai. - [Wan 2.6 image to video](/providers/fal/wan-2-6-image-to-video.md): `fal/wan-2-6-image-to-video`, usage based, the maximum is shown before a run. Needs prompt and image url. Served by fal.ai. - [LTX 2.5 Pro image to video](/providers/fal/ltx-2-5-pro-image-to-video.md): `fal/ltx-2-5-pro-image-to-video`, usage based, the maximum is shown before a run. Needs prompt and image url. Served by fal.ai. - [LTX 2.5 Pro text to video](/providers/fal/ltx-2-5-pro-text-to-video.md): `fal/ltx-2-5-pro-text-to-video`, usage based, the maximum is shown before a run. Needs prompt. Served by fal.ai. - [Luma Ray 3.2 image to video](/providers/fal/luma-ray-3-2-image-to-video.md): `fal/luma-ray-3-2-image-to-video`, from $0.03 per second. Needs prompt. Served by fal.ai. - [Luma Ray 3.2 text to video](/providers/fal/luma-ray-3-2-text-to-video.md): `fal/luma-ray-3-2-text-to-video`, from $0.1 per second. Needs prompt. Served by fal.ai. - [PixVerse V5.6 image to video](/providers/fal/pixverse-5-6-image-to-video.md): `fal/pixverse-5-6-image-to-video`, usage based, the maximum is shown before a run. Needs prompt and image url. Served by fal.ai. - [PixVerse V5.6 text to video](/providers/fal/pixverse-5-6-text-to-video.md): `fal/pixverse-5-6-text-to-video`, usage based, the maximum is shown before a run. Needs prompt. Served by fal.ai. - [Grok Imagine Video 1.5 image to video](/providers/fal/grok-imagine-video-1-5-image-to-video.md): `fal/grok-imagine-video-1-5-image-to-video`, usage based, the maximum is shown before a run. Needs prompt and image url. Served by fal.ai. - [Grok Imagine Video 1.5 Lite image to video](/providers/fal/xai-grok-imagine-video-v1-5-lite-image-to-video.md): `fal/xai-grok-imagine-video-v1-5-lite-image-to-video`, usage based, the maximum is shown before a run. Needs prompt and image url. Served by fal.ai. - [Grok Imagine Video 1.5 Lite text to video](/providers/fal/xai-grok-imagine-video-v1-5-lite-text-to-video.md): `fal/xai-grok-imagine-video-v1-5-lite-text-to-video`, usage based, the maximum is shown before a run. Needs prompt. Served by fal.ai. - [Grok Imagine Video 1.5 reference to video](/providers/fal/xai-grok-imagine-video-v1-5-reference-to-video.md): `fal/xai-grok-imagine-video-v1-5-reference-to-video`, usage based, the maximum is shown before a run. Needs prompt and reference image urls. Served by fal.ai. - [Grok Imagine Video 1.5 text to video](/providers/fal/grok-imagine-video-1-5-text-to-video.md): `fal/grok-imagine-video-1-5-text-to-video`, usage based, the maximum is shown before a run. Needs prompt. Served by fal.ai. - [Vidu Q3 image to video](/providers/fal/vidu-q3-image-to-video.md): `fal/vidu-q3-image-to-video`, usage based, the maximum is shown before a run. Needs image url. Served by fal.ai. - [Vidu Q3 text to video](/providers/fal/vidu-q3-text-to-video.md): `fal/vidu-q3-text-to-video`, usage based, the maximum is shown before a run. Needs prompt. Served by fal.ai. - [OmniHuman 1.5 talking avatar from image and audio](/providers/fal/omnihuman-1-5.md): `fal/omnihuman-1-5`, usage based, the maximum is shown before a run. Needs image url and audio url. Served by fal.ai. - [HeyGen lipsync precision v3](/providers/fal/heygen-v3-lipsync-precision.md): `fal/heygen-v3-lipsync-precision`, usage based, the maximum is shown before a run. Needs video url and audio url. Served by fal.ai. - [HeyGen lipsync speed v3](/providers/fal/heygen-v3-lipsync-speed.md): `fal/heygen-v3-lipsync-speed`, usage based, the maximum is shown before a run. Needs video url and audio url. Served by fal.ai. - [Sync-3 lipsync of a video to an audio track](/providers/fal/sync-lipsync-v3.md): `fal/sync-lipsync-v3`, $8.00 per unit. Needs video url and audio url. Served by fal.ai. - [VEED lipsync](/providers/fal/veed-lipsync.md): `fal/veed-lipsync`, usage based, the maximum is shown before a run. Needs video url and audio url. Served by fal.ai. - [VEED Lipsync v2 lipsync a video to an audio track](/providers/fal/veed-lipsync-v2.md): `fal/veed-lipsync-v2`, $0.07 per unit. Needs video url and audio url. Served by fal.ai. - [Bria video background removal green screen despill](/providers/fal/bria-video-background-removal-green-screen-despill.md): `fal/bria-video-background-removal-green-screen-despill`, usage based, the maximum is shown before a run. Needs video url. Served by fal.ai. - [Flux 3 draft enhance](/providers/fal/blackforestlabs-flux-3-draft-enhance.md): `fal/blackforestlabs-flux-3-draft-enhance`, usage based, the maximum is shown before a run. Needs draft cache url. Served by fal.ai. - [Flux 3 extend video](/providers/fal/blackforestlabs-flux-3-extend-video.md): `fal/blackforestlabs-flux-3-extend-video`, usage based, the maximum is shown before a run. Needs prompt and video url. Served by fal.ai. - [Flux 3 extend video draft](/providers/fal/blackforestlabs-flux-3-extend-video-draft.md): `fal/blackforestlabs-flux-3-extend-video-draft`, $0.12 per second. Needs prompt and video url. Served by fal.ai. - [Flux 3 first and last frame to video](/providers/fal/blackforestlabs-flux-3-first-last-frame-to-video.md): `fal/blackforestlabs-flux-3-first-last-frame-to-video`, usage based, the maximum is shown before a run. Needs prompt, start image url and end image url. Served by fal.ai. - [Flux 3 first and last frame to video draft](/providers/fal/blackforestlabs-flux-3-first-last-frame-to-video-draft.md): `fal/blackforestlabs-flux-3-first-last-frame-to-video-draft`, $0.06 per second. Needs prompt, start image url and end image url. Served by fal.ai. - [FLUX 3 image to video](/providers/fal/blackforestlabs-flux-3-image-to-video.md): `fal/blackforestlabs-flux-3-image-to-video`, usage based, the maximum is shown before a run. Needs prompt and image url. Served by fal.ai. - [Flux 3 image to video draft](/providers/fal/blackforestlabs-flux-3-image-to-video-draft.md): `fal/blackforestlabs-flux-3-image-to-video-draft`, $0.06 per second. Needs prompt and image url. Served by fal.ai. - [Flux 3 keyframes to video](/providers/fal/blackforestlabs-flux-3-keyframes-to-video.md): `fal/blackforestlabs-flux-3-keyframes-to-video`, usage based, the maximum is shown before a run. Needs prompt and keyframes. Served by fal.ai. - [Flux 3 keyframes to video draft](/providers/fal/blackforestlabs-flux-3-keyframes-to-video-draft.md): `fal/blackforestlabs-flux-3-keyframes-to-video-draft`, $0.06 per second. Needs prompt and keyframes. Served by fal.ai. - [Flux 3 text to video](/providers/fal/blackforestlabs-flux-3-text-to-video.md): `fal/blackforestlabs-flux-3-text-to-video`, usage based, the maximum is shown before a run. Needs prompt. Served by fal.ai. - [Flux 3 text to video draft](/providers/fal/blackforestlabs-flux-3-text-to-video-draft.md): `fal/blackforestlabs-flux-3-text-to-video-draft`, $0.06 per second. Needs prompt. Served by fal.ai. - [Flux 3 video edit](/providers/fal/blackforestlabs-flux-3-edit-video.md): `fal/blackforestlabs-flux-3-edit-video`, usage based, the maximum is shown before a run. Needs prompt and video url. Served by fal.ai. - [HeyGen avatar3 digital twin](/providers/fal/heygen-avatar3-digital-twin.md): `fal/heygen-avatar3-digital-twin`, usage based, the maximum is shown before a run. Needs character and voice. Served by fal.ai. - [HeyGen avatar4 digital twin](/providers/fal/heygen-avatar4-digital-twin.md): `fal/heygen-avatar4-digital-twin`, usage based, the maximum is shown before a run. Needs character and voice. Served by fal.ai. - [HeyGen image to video avatar4](/providers/fal/heygen-avatar4-image-to-video.md): `fal/heygen-avatar4-image-to-video`, usage based, the maximum is shown before a run. Needs image url. Served by fal.ai. - [HeyGen v2 translate precision](/providers/fal/heygen-v2-translate-precision.md): `fal/heygen-v2-translate-precision`, usage based, the maximum is shown before a run. Needs video url and output language. Served by fal.ai. - [HeyGen v2 translate speed](/providers/fal/heygen-v2-translate-speed.md): `fal/heygen-v2-translate-speed`, usage based, the maximum is shown before a run. Needs video url and output language. Served by fal.ai. - [HeyGen v2 video agent](/providers/fal/heygen-v2-video-agent.md): `fal/heygen-v2-video-agent`, usage based, the maximum is shown before a run. Needs prompt. Served by fal.ai. - [HeyGen v3 filler word removal](/providers/fal/heygen-v3-filler-word-removal.md): `fal/heygen-v3-filler-word-removal`, usage based, the maximum is shown before a run. Needs video url. Served by fal.ai. - [HeyGen v5 digital twin](/providers/fal/heygen-avatar5-digital-twin.md): `fal/heygen-avatar5-digital-twin`, usage based, the maximum is shown before a run. Takes fit, avatar, resolution and more, all optional. Served by fal.ai. - [HeyGen video agent v3](/providers/fal/heygen-v3-video-agent.md): `fal/heygen-v3-video-agent`, usage based, the maximum is shown before a run. Needs prompt. Served by fal.ai. - [Luma Ray 3.2 reframe agent](/providers/fal/luma-agent-ray-v3-2-reframe.md): `fal/luma-agent-ray-v3-2-reframe`, usage based, the maximum is shown before a run. Needs prompt, video url and aspect ratio. Served by fal.ai. - [Luma Ray 3.2 video to video agent](/providers/fal/luma-agent-ray-v3-2-video-to-video.md): `fal/luma-agent-ray-v3-2-video-to-video`, usage based, the maximum is shown before a run. Needs prompt and video url. Served by fal.ai. - [VEED avatars audio to video](/providers/fal/veed-avatars-audio-to-video.md): `fal/veed-avatars-audio-to-video`, usage based, the maximum is shown before a run. Needs avatar id and audio url. Served by fal.ai. - [VEED avatars text to video](/providers/fal/veed-avatars-text-to-video.md): `fal/veed-avatars-text-to-video`, usage based, the maximum is shown before a run. Needs avatar id and text. Served by fal.ai. - [VEED Fabric 1.0](/providers/fal/veed-fabric-1-0.md): `fal/veed-fabric-1-0`, usage based, the maximum is shown before a run. Needs image url, audio url and resolution. Served by fal.ai. - [VEED Fabric 1.0 fast](/providers/fal/veed-fabric-1-0-fast.md): `fal/veed-fabric-1-0-fast`, usage based, the maximum is shown before a run. Needs image url, audio url and resolution. Served by fal.ai. - [VEED Fabric 1.0 text](/providers/fal/veed-fabric-1-0-text.md): `fal/veed-fabric-1-0-text`, usage based, the maximum is shown before a run. Needs image url, text and resolution. Served by fal.ai. - [VEED subtitles](/providers/fal/veed-subtitles.md): `fal/veed-subtitles`, usage based, the maximum is shown before a run. Needs video url and preset. Served by fal.ai. - [VEED video background removal](/providers/fal/veed-video-background-removal.md): `fal/veed-video-background-removal`, usage based, the maximum is shown before a run. Needs video url. Served by fal.ai. - [VEED video background removal fast](/providers/fal/veed-video-background-removal-fast.md): `fal/veed-video-background-removal-fast`, usage based, the maximum is shown before a run. Needs video url. Served by fal.ai. - [VEED video background removal green screen](/providers/fal/veed-video-background-removal-green-screen.md): `fal/veed-video-background-removal-green-screen`, usage based, the maximum is shown before a run. Needs video url. Served by fal.ai. ## Related - [AI image generation](/tools/image-generation.md): 98 tools, from $0.01 per call, some tools free. - [AI audio](/tools/audio-generation.md): 21 tools, from $0.002 per second. ## Providers - [fal.ai](/providers/fal.md): 214 tools, from $0.01 per call, some tools free. ## Questions ### Which models can my agent run? Seedance, Kling, Veo 3.1, Gemini Omni, MiniMax Hailuo, Wan, LTX and 6 more. ### Which providers serve AI video generation tools? fal.ai. Your agent compares them by price and inputs before it runs one. ### How is it billed? Per call, at the provider's price with no markup, from $0.002 per second. Your agent sees the price before it runs a tool. [Tools](/tools.md) · [Connection guide](/connect.md) · [Billing](/docs/billing.md) --- [HTML page](/tools/video-generation) · [Agent index](/llms.txt)