docs: align legacy model descriptions

web/components/dashboard.tsx

@@ -514,7 +514,7 @@ export const Dashboard = forwardRef<DashboardHandle, Props>(function Dashboard({
                 )}
                 {!hasFrames ? (
                   <KanbanCard tone="pink" tags={["分镜"]} title="等待解析后抽取">
-                    <div className="text-[11.5px] text-[var(--text-soft)]">候选 30 张 → pHash 去重 + 清晰度排序 → 时序分桶 → 5 张代表分镜</div>
+                    <div className="text-[11.5px] text-[var(--text-soft)]">候选帧 → pHash 去重 + 清晰度排序 + 时序分桶 → 按当前设置产出参考帧</div>
                   </KanbanCard>
                 ) : (
                   job!.frames.map((f) => {
@@ -646,7 +646,7 @@ export const Dashboard = forwardRef<DashboardHandle, Props>(function Dashboard({
                     <audio controls className="h-8 w-full" src={apiAssetUrl(job.audio_script.voice_url)} />
                   ) : (
                     <div className="text-[11px] text-[var(--text-soft)]">
-                      {job?.audio_script?.error || "配置 Azure OpenAI TTS 后自动生成配音文件"}
+                      {job?.audio_script?.error || "当前第一步不默认生成配音文件；后续新配音阶段走 Azure OpenAI TTS"}
                     </div>
                   )}
                   <div className="kanban-meta">{job?.audio_script?.voice_id || "Azure voice"}</div>