Video generation

OpenClaw agents can generate videos from text prompts, reference images, or existing videos. Sixteen provider backends are supported, each with different model options, input modes, and feature sets. The agent picks the right provider automatically based on your configuration and available API keys.

Note

The video_generate tool only appears when at least one video-generation provider is available. If you do not see it in your agent tools, set a provider API key or configure agents.defaults.videoGenerationModel.

OpenClaw treats video generation as three runtime modes:

• generate - text-to-video requests with no reference media.
• imageToVideo - request includes one or more reference images.
• videoToVideo - request includes one or more reference videos.

Providers can support any subset of those modes. The tool validates the active mode before submission and reports supported modes in action=list.

Quick start

1. Configure auth

   Set an API key for any supported provider:

   export GEMINI_API_KEY="your-key"

2. Pick a default model (optional)

   openclaw config set agents.defaults.videoGenerationModel.primary "google/veo-3.1-fast-generate-preview"

3. Ask the agent

   Generate a 5-second cinematic video of a friendly lobster surfing at sunset.

   The agent calls video_generate automatically. No tool allowlisting is needed.

How async generation works

Video generation is asynchronous. When the agent calls video_generate in a session:

1. OpenClaw submits the request to the provider and immediately returns a task id.
2. The provider processes the job in the background (typically 30 seconds to several minutes depending on the provider and resolution; slow queue-backed providers can run up to the configured timeout).
3. When the video is ready, OpenClaw wakes the same session with an internal completion event.
4. The agent tells the user through the session’s normal visible-reply mode: final reply delivery when automatic, or message(action="send") when the session requires the message tool. If the requester session is inactive or its active wake fails, and some generated video is still missing from the completion reply, OpenClaw sends an idempotent direct fallback with only the missing video.

While a job is in flight, duplicate video_generate calls in the same session return the current task status instead of starting another generation. Use openclaw tasks list or openclaw tasks show <taskId> to check progress from the CLI.

Outside of session-backed agent runs (for example, direct tool invocations), the tool falls back to inline generation and returns the final media path in the same turn.

Generated video files are saved under OpenClaw-managed media storage when the provider returns bytes. The default generated-video save cap follows the video media limit, and agents.defaults.mediaMaxMb raises it for larger renders. When a provider also returns a hosted output URL, OpenClaw can deliver that URL instead of failing the task if local persistence rejects an oversized file.

Task lifecycle

State	Meaning
queued	Task created, waiting for the provider to accept it.
running	Provider is processing (typically 30 seconds to several minutes depending on provider and resolution).
succeeded	Video ready; the agent wakes and posts it to the conversation.
failed	Provider error or timeout; the agent wakes with error details.

Check status from the CLI:

openclaw tasks list
openclaw tasks show <taskId>
openclaw tasks cancel <taskId>

If a video task is already queued or running for the current session, video_generate returns the existing task status instead of starting a new one. Use action: "status" to check explicitly without triggering a new generation.

Supported providers

Provider	Default model	Text	Image ref	Video ref	Auth
Alibaba	wan2.6-t2v	✓	Yes (remote URL)	Yes (remote URL)	MODELSTUDIO_API_KEY
BytePlus (1.0)	seedance-1-0-pro-250528	✓	Up to 2 images (I2V models only; first + last frame)	-	BYTEPLUS_API_KEY
BytePlus Seedance 1.5	seedance-1-5-pro-251215	✓	Up to 2 images (first + last frame via role)	-	BYTEPLUS_API_KEY
BytePlus Seedance 2.0	dreamina-seedance-2-0-260128	✓	Up to 9 reference images	Up to 3 videos	BYTEPLUS_API_KEY
ComfyUI	workflow	✓	1 image	-	COMFY_API_KEY or COMFY_CLOUD_API_KEY
DeepInfra	Pixverse/Pixverse-T2V	✓	-	-	DEEPINFRA_API_KEY
fal	fal-ai/minimax/video-01-live	✓	1 image; up to 9 with Seedance reference-to-video	Up to 3 videos with Seedance reference-to-video	FAL_KEY
Google	veo-3.1-fast-generate-preview	✓	1 image	1 video	GEMINI_API_KEY
MiniMax	MiniMax-Hailuo-2.3	✓	1 image	-	MINIMAX_API_KEY or MiniMax OAuth
OpenAI	sora-2	✓	1 image	1 video	OPENAI_API_KEY
OpenRouter	google/veo-3.1-fast	✓	Up to 4 images (first/last frame or references)	-	OPENROUTER_API_KEY
Qwen	wan2.6-t2v	✓	Yes (remote URL)	Yes (remote URL)	QWEN_API_KEY
Runway	gen4.5	✓	1 image	1 video	RUNWAYML_API_SECRET
Together	Wan-AI/Wan2.2-T2V-A14B	✓	Wan-AI/Wan2.2-I2V-A14B only	-	TOGETHER_API_KEY
Vydra	veo3	✓	1 image (kling)	-	VYDRA_API_KEY
xAI	grok-imagine-video	✓	1 first-frame image or up to 7 reference_images	1 video	XAI_API_KEY

Some providers accept additional or alternate API key env vars. See individual provider pages for details.

Run video_generate action=list to inspect available providers, models, and runtime modes at runtime.

Capability matrix

The explicit mode contract used by video_generate, contract tests, and the shared live sweep:

Provider	generate	imageToVideo	videoToVideo	Shared live lanes today
Alibaba	✓	✓	✓	generate, imageToVideo; videoToVideo skipped because this provider needs remote http(s) video URLs
BytePlus	✓	✓	-	generate, imageToVideo
ComfyUI	✓	✓	-	Not in the shared sweep; workflow-specific coverage lives with Comfy tests
DeepInfra	✓	-	-	generate; native DeepInfra video schemas are text-to-video in the plugin contract
fal	✓	✓	✓	generate, imageToVideo; videoToVideo only when using Seedance reference-to-video
Google	✓	✓	✓	generate, imageToVideo; shared videoToVideo skipped because the current buffer-backed Gemini/Veo sweep does not accept that input
MiniMax	✓	✓	-	generate, imageToVideo
OpenAI	✓	✓	✓	generate, imageToVideo; shared videoToVideo skipped because this org/input path currently needs provider-side video edit access
OpenRouter	✓	✓	-	generate, imageToVideo
Qwen	✓	✓	✓	generate, imageToVideo; videoToVideo skipped because this provider needs remote http(s) video URLs
Runway	✓	✓	✓	generate, imageToVideo; videoToVideo runs only when the selected model is runway/gen4_aleph
Together	✓	✓	-	generate, imageToVideo
Vydra	✓	✓	-	generate; shared imageToVideo skipped because bundled veo3 is text-only and bundled kling requires a remote image URL
xAI	✓	✓	✓	generate, imageToVideo; videoToVideo skipped because this provider currently needs a remote MP4 URL

Tool parameters

Required

Text description of the video to generate. Required for `action: "generate"`.

Content inputs

Single reference image (path or URL). Multiple reference images (up to 9). Optional per-position role hints parallel to the combined image list. Canonical values: first_frame, last_frame, reference_image. Single reference video (path or URL). Multiple reference videos (up to 4). Optional per-position role hints parallel to the combined video list. Canonical value: reference_video. Single reference audio (path or URL). Used for background music or voice reference when the provider supports audio inputs. Multiple reference audios (up to 3). Optional per-position role hints parallel to the combined audio list. Canonical value: reference_audio.

Note

Role hints are forwarded to the provider as-is. Canonical values come from the VideoGenerationAssetRole union but providers may accept additional role strings. *Roles arrays must not have more entries than the corresponding reference list; off-by-one mistakes fail with a clear error. Use an empty string to leave a slot unset. For xAI, set every image role to reference_image to use its reference_images generation mode; omit the role or use first_frame for single-image image-to-video.

Style controls

Aspect-ratio hint such as `1:1`, `16:9`, `9:16`, `adaptive`, or a provider-specific value. OpenClaw normalizes or ignores unsupported values per provider. Resolution hint such as `480P`, `720P`, `768P`, `1080P`, `4K`, or a provider-specific value. OpenClaw normalizes or ignores unsupported values per provider. Target duration in seconds (rounded to nearest provider-supported value). Size hint when the provider supports it. Enable generated audio in the output when supported. Distinct from `audioRef*` (inputs). Toggle provider watermarking when supported.

adaptive is a provider-specific sentinel: it is forwarded as-is to providers that declare adaptive in their capabilities (e.g. BytePlus Seedance uses it to auto-detect the ratio from the input image dimensions). Providers that do not declare it surface the value via details.ignoredOverrides in the tool result so the drop is visible.

Advanced

`"status"` returns the current session task; `"list"` inspects providers. Provider/model override (e.g. `runway/gen4.5`). Output filename hint. Optional provider operation timeout in milliseconds. When omitted, OpenClaw uses `agents.defaults.videoGenerationModel.timeoutMs` if configured, otherwise the plugin-authored provider default when one exists. Provider-specific options as a JSON object (e.g. `{"seed": 42, "draft": true}`). Providers that declare a typed schema validate the keys and types; unknown keys or mismatches skip the candidate during fallback. Providers without a declared schema receive the options as-is. Run `video_generate action=list` to see what each provider accepts.

Note

Not all providers support all parameters. OpenClaw normalizes duration to the closest provider-supported value, and remaps translated geometry hints such as size-to-aspect-ratio when a fallback provider exposes a different control surface. Truly unsupported overrides are ignored on a best-effort basis and reported as warnings in the tool result. Hard capability limits (such as too many reference inputs) fail before submission. Tool results report applied settings; details.normalization captures any requested-to-applied translation.

Reference inputs select the runtime mode:

• No reference media → generate
• Any image reference → imageToVideo
• Any video reference → videoToVideo
• Reference audio inputs do not change the resolved mode; they apply on top of whatever mode the image/video references select, and only work with providers that declare maxInputAudios.

Mixed image and video references are not a stable shared capability surface. Prefer one reference type per request.

Fallback and typed options

Some capability checks are applied at the fallback layer rather than the tool boundary, so a request that exceeds the primary provider’s limits can still run on a capable fallback:

• Active candidate declaring no maxInputAudios (or 0) is skipped when the request contains audio references; next candidate is tried.
• Active candidate’s maxDurationSeconds below the requested durationSeconds with no declared supportedDurationSeconds list → skipped.
• Request contains providerOptions and the active candidate explicitly declares a typed providerOptions schema → skipped if supplied keys are not in the schema or value types do not match. Providers without a declared schema receive options as-is (backward-compatible pass-through). A provider can opt out of all provider options by declaring an empty schema (capabilities.providerOptions: {}), which causes the same skip as a type mismatch.

The first skip reason in a request logs at warn so operators see when their primary provider was passed over; subsequent skips log at debug to keep long fallback chains quiet. If every candidate is skipped, the aggregated error includes the skip reason for each.

Actions

Action	What it does
generate	Default. Create a video from the given prompt and optional reference inputs.
status	Check the state of the in-flight video task for the current session without starting another generation.
list	Show available providers, models, and their capabilities.

Model selection

OpenClaw resolves the model in this order:

1. model tool parameter - if the agent specifies one in the call.
2. videoGenerationModel.primary from config.
3. videoGenerationModel.fallbacks in order.
4. Auto-detection - providers that have valid auth, starting with the current default provider, then remaining providers in alphabetical order.

If a provider fails, the next candidate is tried automatically. If all candidates fail, the error includes details from each attempt.

Set agents.defaults.mediaGenerationAutoProviderFallback: false to use only the explicit model, primary, and fallbacks entries.

{
  agents: {
    defaults: {
      videoGenerationModel: {
        primary: "google/veo-3.1-fast-generate-preview",
        fallbacks: ["runway/gen4.5", "qwen/wan2.6-t2v"],
      },
    },
  },
}

Provider notes

Alibaba

Uses DashScope / Model Studio async endpoint. Reference images and videos must be remote http(s) URLs.

BytePlus (1.0)

Provider id: byteplus.

Models: seedance-1-0-pro-250528 (default), seedance-1-0-pro-t2v-250528, seedance-1-0-pro-fast-251015, seedance-1-0-lite-t2v-250428, seedance-1-0-lite-i2v-250428.

T2V models (*-t2v-*) do not accept image inputs; I2V models and general *-pro-* models support a single reference image (first frame). Pass the image positionally or set role: "first_frame". T2V model IDs are automatically switched to the corresponding I2V variant when an image is provided.

Supported providerOptions keys: seed (number), draft (boolean - forces 480p), camera_fixed (boolean).

BytePlus Seedance 1.5

Requires the @openclaw/byteplus-modelark plugin. Provider id: byteplus-seedance15. Model: seedance-1-5-pro-251215.

Uses the unified content[] API. Supports at most 2 input images (first_frame + last_frame). All inputs must be remote https:// URLs. Set role: "first_frame" / "last_frame" on each image, or pass images positionally.

aspectRatio: "adaptive" auto-detects ratio from the input image. audio: true maps to generate_audio. providerOptions.seed (number) is forwarded.

BytePlus Seedance 2.0

Requires the @openclaw/byteplus-modelark plugin. Provider id: byteplus-seedance2. Models: dreamina-seedance-2-0-260128, dreamina-seedance-2-0-fast-260128.

Uses the unified content[] API. Supports up to 9 reference images, 3 reference videos, and 3 reference audios. All inputs must be remote https:// URLs. Set role on each asset - supported values: "first_frame", "last_frame", "reference_image", "reference_video", "reference_audio".

aspectRatio: "adaptive" auto-detects ratio from the input image. audio: true maps to generate_audio. providerOptions.seed (number) is forwarded.

ComfyUI

Workflow-driven local or cloud execution. Supports text-to-video and image-to-video through the configured graph.

fal

Uses a queue-backed flow for long-running jobs. OpenClaw waits up to 20 minutes by default before treating an in-progress fal queue job as timed out. Most fal video models accept a single image reference. Seedance 2.0 reference-to-video models accept up to 9 images, 3 videos, and 3 audio references, with at most 12 total reference files.

Google (Gemini / Veo)

Supports one image or one video reference. Generated-audio requests are ignored with a warning on the Gemini API path because that API rejects the generateAudio parameter for current Veo video generation.

MiniMax

Single image reference only. MiniMax accepts 768P and 1080P resolutions; requests such as 720P are normalized to the closest supported value before submission.

OpenAI

Only size override is forwarded. Other style overrides (aspectRatio, resolution, audio, watermark) are ignored with a warning.

OpenRouter

Uses OpenRouter’s asynchronous /videos API. OpenClaw submits the job, polls polling_url, and downloads either unsigned_urls or the documented job content endpoint. The bundled google/veo-3.1-fast default advertises 4/6/8 second durations, 720P/1080P resolutions, and 16:9/9:16 aspect ratios.

Qwen

Same DashScope backend as Alibaba. Reference inputs must be remote http(s) URLs; local files are rejected upfront.

Runway

Supports local files via data URIs. Video-to-video requires runway/gen4_aleph. Text-only runs expose 16:9 and 9:16 aspect ratios.

Together

Single image reference only.

Vydra

Uses https://www.vydra.ai/api/v1 directly to avoid auth-dropping redirects. veo3 is bundled as text-to-video only; kling requires a remote image URL.

xAI

Supports text-to-video, single first-frame image-to-video, up to 7 reference_image inputs through xAI reference_images, and remote video edit/extend flows.

Provider capability modes

The shared video-generation contract supports mode-specific capabilities instead of only flat aggregate limits. New provider implementations should prefer explicit mode blocks:

capabilities: {
  generate: {
    maxVideos: 1,
    maxDurationSeconds: 10,
    supportsResolution: true,
  },
  imageToVideo: {
    enabled: true,
    maxVideos: 1,
    maxInputImages: 1,
    maxInputImagesByModel: { "provider/reference-to-video": 9 },
    maxDurationSeconds: 5,
  },
  videoToVideo: {
    enabled: true,
    maxVideos: 1,
    maxInputVideos: 1,
    maxDurationSeconds: 5,
  },
}

Flat aggregate fields such as maxInputImages and maxInputVideos are not enough to advertise transform-mode support. Providers should declare generate, imageToVideo, and videoToVideo explicitly so live tests, contract tests, and the shared video_generate tool can validate mode support deterministically.

When one model in a provider has wider reference-input support than the rest, use maxInputImagesByModel, maxInputVideosByModel, or maxInputAudiosByModel instead of raising the mode-wide limit.

Live tests

Opt-in live coverage for the shared bundled providers:

OPENCLAW_LIVE_TEST=1 pnpm test:live -- extensions/video-generation-providers.live.test.ts

Repo wrapper:

pnpm test:live:media video

This live file uses already-exported provider env vars ahead of stored auth profiles by default, and runs a release-safe smoke by default:

• generate for every non-FAL provider in the sweep.
• One-second lobster prompt.
• Per-provider operation cap from OPENCLAW_LIVE_VIDEO_GENERATION_TIMEOUT_MS (180000 by default).

FAL is opt-in because provider-side queue latency can dominate release time:

pnpm test:live:media video --video-providers fal

Set OPENCLAW_LIVE_VIDEO_GENERATION_FULL_MODES=1 to also run declared transform modes the shared sweep can exercise safely with local media:

• imageToVideo when capabilities.imageToVideo.enabled.
• videoToVideo when capabilities.videoToVideo.enabled and the provider/model accepts buffer-backed local video input in the shared sweep.

Today the shared videoToVideo live lane covers runway only when you select runway/gen4_aleph.

Configuration

Set the default video-generation model in your OpenClaw config:

{
  agents: {
    defaults: {
      videoGenerationModel: {
        primary: "qwen/wan2.6-t2v",
        fallbacks: ["qwen/wan2.6-r2v-flash"],
      },
    },
  },
}

Or via the CLI:

openclaw config set agents.defaults.videoGenerationModel.primary "qwen/wan2.6-t2v"

Related

• Alibaba Model Studio
• Background tasks - task tracking for async video generation
• BytePlus
• ComfyUI
• Configuration reference
• fal
• Google (Gemini)
• MiniMax
• Models
• OpenAI
• Qwen
• Runway
• Together AI
• Tools overview
• Vydra
• xAI