diff --git a/web/src/lib/model-selection.ts b/web/src/lib/model-selection.ts
index 45c34bc94..fab37d7c3 100644
--- a/web/src/lib/model-selection.ts
+++ b/web/src/lib/model-selection.ts
@@ -248,6 +248,8 @@ export function defaultImageParamsForModel(config: AiConfig, model: string): Pic
 
 export type ModelGenerationDefaults = Pick<AiConfig, "size" | "quality" | "transparentBackground" | "count" | "videoSeconds" | "vquality" | "videoGenerateAudio" | "videoWatermark">;
 
+type ModelVideoBooleanOptions = Pick<AiConfig, "videoGenerateAudio" | "videoWatermark">;
+
 export function resolveModelGenerationDefaults(
     config: AiConfig,
     model: string,
@@ -294,6 +296,20 @@ export function resolveModelGenerationDefaults(
     return {};
 }
 
+export function resolveModelVideoBooleanOptions(
+    config: AiConfig,
+    model: string,
+    explicit: Partial<ModelVideoBooleanOptions> = {},
+    fallback: Partial<ModelVideoBooleanOptions> = {},
+): ModelVideoBooleanOptions {
+    const profile = modelCapabilityConfigFor(config, model).video!;
+    const defaults = resolveModelGenerationDefaults(config, model, "video", explicit, fallback);
+    return {
+        videoGenerateAudio: profile.generateAudio.supported ? defaults.videoGenerateAudio ?? String(profile.generateAudio.default) : "false",
+        videoWatermark: profile.watermark.supported ? defaults.videoWatermark ?? String(profile.watermark.default) : "false",
+    };
+}
+
 export function maxModelInputCapacity(config: AiConfig, capability: "image" | "video", kind: "image" | "video" | "audio") {
     const options = selectableModelsByCapability(config, capability);
     if (!options.length) return null;
diff --git a/web/src/pages/projects/detail/workflow-production-workbench.tsx b/web/src/pages/projects/detail/workflow-production-workbench.tsx
index 44fcefdd7..c33d7a823 100644
--- a/web/src/pages/projects/detail/workflow-production-workbench.tsx
+++ b/web/src/pages/projects/detail/workflow-production-workbench.tsx
@@ -11,7 +11,7 @@ import { CreditSymbol, requestCreditCost } from "@/constant/credits";
 import { modelCapabilityConfigFor, normalizeImageValue, normalizeVideoValue, videoDurationOptions } from "@/lib/model-capabilities";
 import { modelQuoteRequest } from "@/lib/model-pricing";
 import { customShotTitle, formatShotOrdinal, normalizeDefaultShotTitle } from "@/lib/shot-label";
-import { modelCompatibilityError, resolveCompatibleModel, type ModelRequirements } from "@/lib/model-selection";
+import { modelCompatibilityError, resolveCompatibleModel, resolveModelVideoBooleanOptions, type ModelRequirements } from "@/lib/model-selection";
 import { formatVideoResolutionLabel } from "@/lib/video-generation-options";
 import { submitBackendGenerationTask } from "@/services/api/generation-task";
 import { quoteLogicalModel } from "@/services/api/logical-models";
@@ -145,6 +145,12 @@ export default function WorkflowProductionWorkbench(props: Props) {
     const activeProfile = useMemo(() => modelCapabilityConfigFor(effectiveConfig, routedModel), [effectiveConfig, routedModel]);
     const videoProfile = generationCapability === "video" ? activeProfile.video : undefined;
     const imageProfile = generationCapability === "image" ? activeProfile.image : undefined;
+    const videoBooleanOptions = useMemo(() => generationCapability === "video"
+        ? resolveModelVideoBooleanOptions(effectiveConfig, routedModel, {}, {
+              videoGenerateAudio: effectiveConfig.videoGenerateAudio,
+              videoWatermark: effectiveConfig.videoWatermark,
+          })
+        : undefined, [effectiveConfig, generationCapability, routedModel]);
     const generationConfig = useMemo(() => ({
         ...effectiveConfig,
         model: routedModel,
@@ -154,7 +160,8 @@ export default function WorkflowProductionWorkbench(props: Props) {
         quality: imageQuality,
         vquality: resolution,
         videoSeconds: generationSeconds,
-    }), [aspectRatio, effectiveConfig, generationCapability, generationSeconds, imageQuality, resolution, routedModel]);
+        ...(videoBooleanOptions || {}),
+    }), [aspectRatio, effectiveConfig, generationCapability, generationSeconds, imageQuality, resolution, routedModel, videoBooleanOptions]);
     const priceChannel = resolveModelChannel(generationConfig, routedModel);
     const configuredCredits = requestCreditCost({
         channelMode: priceChannel.scope === "system" ? "remote" : "local",
diff --git a/web/test/canvas-model-policy.test.ts b/web/test/canvas-model-policy.test.ts
index 829f3f43c..34ec3c760 100644
--- a/web/test/canvas-model-policy.test.ts
+++ b/web/test/canvas-model-policy.test.ts
@@ -3,7 +3,7 @@ import { describe, expect, test } from "bun:test";
 import { canvasConnectionError } from "../src/lib/canvas/canvas-connection-policy";
 import { assertCanvasImageReferenceLimit, buildGenerationConfig, canvasImageReferenceLimitError, resolveCanvasGenerationModel } from "../src/lib/canvas/canvas-project-generation";
 import { defaultModelCapabilityConfig } from "../src/lib/model-capabilities";
-import { groupModelsByDisplayName, inferVideoOperation, modelCompatibilityError, modelGroupReferenceLimits, modelPromptLengthError, resolveCompatibleModel, resolveModelGenerationDefaults } from "../src/lib/model-selection";
+import { groupModelsByDisplayName, inferVideoOperation, modelCompatibilityError, modelGroupReferenceLimits, modelPromptLengthError, resolveCompatibleModel, resolveModelGenerationDefaults, resolveModelVideoBooleanOptions } from "../src/lib/model-selection";
 import { defaultConfig, normalizeModelOptionValue, type AiConfig, type ModelChannel } from "../src/stores/use-config-store";
 import { CanvasNodeType, type CanvasConnection, type CanvasNodeData } from "../src/types/canvas";
 
@@ -141,6 +141,59 @@ describe("逻辑模型选择", () => {
         expect(resolveModelGenerationDefaults(config, model, "video", {}, { videoSeconds: "6" }).videoSeconds).toBe("15");
     });
 
+    test("镜头视频不会向不支持同步音频的模型提交全局 true 默认值", () => {
+        const model = "platform::silent-video";
+        const profile = defaultModelCapabilityConfig(undefined, "silent-video");
+        profile.video!.generateAudio = { supported: false, default: false };
+        profile.video!.watermark = { supported: false, default: false };
+        const config: AiConfig = {
+            ...defaultConfig,
+            videoGenerateAudio: "true",
+            videoWatermark: "true",
+            channels: [{
+                id: "platform",
+                name: "平台模型",
+                baseUrl: "/api",
+                apiKey: "system",
+                apiFormat: "openai",
+                scope: "system",
+                models: ["silent-video"],
+                modelCosts: [{
+                    model: "silent-video",
+                    capability: "video",
+                    billingMode: "per_second",
+                    unitPriceMicrocredits: 1,
+                    logicalModelId: "silent-video",
+                    logicalCapabilitySpec: {
+                        version: 1,
+                        capability: "video",
+                        options: {
+                            videoGenerateAudio: { values: [false] },
+                            videoWatermark: { values: [false] },
+                        },
+                    },
+                    capabilityConfig: profile,
+                }],
+            }],
+            models: [model],
+            videoModels: [model],
+            videoModel: model,
+            model,
+        };
+
+        expect(resolveModelVideoBooleanOptions(config, model, {}, {
+            videoGenerateAudio: config.videoGenerateAudio,
+            videoWatermark: config.videoWatermark,
+        })).toEqual({ videoGenerateAudio: "false", videoWatermark: "false" });
+
+        profile.video!.generateAudio = { supported: true, default: true };
+        config.videoGenerateAudio = "false";
+        expect(resolveModelVideoBooleanOptions(config, model, {}, {
+            videoGenerateAudio: config.videoGenerateAudio,
+            videoWatermark: config.videoWatermark,
+        })).toEqual({ videoGenerateAudio: "true", videoWatermark: "false" });
+    });
+
 
     test("渠道视频能力配置优先于旧的全局 6 秒和 1:1 配置", () => {
         const model = "autodl-channel::MiniMax H3";