@starreel/mcp 0.1.112 → 0.1.113

package/dist/tools/produce.js

@@ -816,7 +816,13 @@ export function registerProduceTools(server, client) {
         + '走 TTS 配音的片子不会有这个问题。'
         + '\n★**很慢**:每镜要完整解码音轨,实测 6~10 秒/镜(后端限并发 4),整集几十镜要等几分钟。'
         + '别在产线中途反复调,放在成片前查一次。'
-        + '\n★shots_probe_failed 是**没测成**的镜数,不代表那些镜有问题。', { episode_id: z.number().int().positive() }, async ({ episode_id }) => jsonResult(await client.produceGet(`/episodes/${episode_id}/silent-shot-audio-audit`)));
+        + '\n★shots_probe_failed 是**没测成**的镜数,不代表那些镜有问题。'
+        + '\n★★probe_speech:true 再对**台词栏为空**的镜跑人声检测(已标定判据):厂商在无台词镜里自己念出一句话时,'
+        + '响度比测不出来,这个能——命中的镜列在 unexpected_speech,text 是念出的内容。更慢(每镜下载+转写),'
+        + '一次最多 20 镜,skipped_by_limit 是剩下的、再调一次接着扫。只报不改:由客户决定 mute_only 静掉还是重生成。', {
+        episode_id: z.number().int().positive(),
+        probe_speech: z.boolean().optional().describe('true=对无台词镜额外跑人声检测(慢,一次≤20镜)'),
+    }, async ({ episode_id, probe_speech }) => jsonResult(await client.produceGet(`/episodes/${episode_id}/silent-shot-audio-audit${probe_speech ? '?probe_speech=1' : ''}`)));
     server.tool('get_asset_recovery', '列本集可恢复的**历史视频产物**(免费·只读):以前生成过、后来被覆盖掉的整集成片与逐镜视频。'
         + '\n用途:客户说「上一版那个成片好」「这一镜前天那条视频比现在这条好」时,从这里找回来。'
         + '\n★★只管视频,**不含图片帧**:首尾帧不在这里,列表里也永远不会出现。'

package/openapi.json

@@ -2,8 +2,8 @@
   "openapi": "3.1.0",
   "info": {
     "title": "StarReel Production API",
-    "version": "0.1.112",
-    "description": "Turn a script into a finished, downloadable short-drama episode over REST.\n\nPipeline: script → AI rewrite → cast/scenes/props extraction → storyboards → portraits & sheets + scene plates → keyframes → video shots → TTS → final cut (.mp4).\n\n**Billing is prepaid and agent-safe**: big-ticket stages are quote-then-generate (`quote_*` returns a `quote_id`). For video, quote == actual charge. For images the quote is a *range* — models billed per reference image are priced before those are assembled, so `estimated_points` is the upper bound (size the balance by it and a run never dies half-way) and `typical_points` is the usual cost; fixed-price models return the two equal. Insufficient balance returns 402 — nothing half-runs and the account never goes negative.\n\nAuth: exchange your API key at `POST /v1/agent/token` for a 15-minute bearer token.\n\nGenerated from the @starreel/mcp v0.1.112 tool surface (operationIds match MCP tool names 1:1)."
+    "version": "0.1.113",
+    "description": "Turn a script into a finished, downloadable short-drama episode over REST.\n\nPipeline: script → AI rewrite → cast/scenes/props extraction → storyboards → portraits & sheets + scene plates → keyframes → video shots → TTS → final cut (.mp4).\n\n**Billing is prepaid and agent-safe**: big-ticket stages are quote-then-generate (`quote_*` returns a `quote_id`). For video, quote == actual charge. For images the quote is a *range* — models billed per reference image are priced before those are assembled, so `estimated_points` is the upper bound (size the balance by it and a run never dies half-way) and `typical_points` is the usual cost; fixed-price models return the two equal. Insufficient balance returns 402 — nothing half-runs and the account never goes negative.\n\nAuth: exchange your API key at `POST /v1/agent/token` for a 15-minute bearer token.\n\nGenerated from the @starreel/mcp v0.1.113 tool surface (operationIds match MCP tool names 1:1)."
   },
   "servers": [
     {
@@ -6841,7 +6841,7 @@
       "get": {
         "operationId": "audit_silent_shot_audio",
         "summary": "查**无台词镜里的异常发声**:本该沉默的反应镜,音轨却比同场说话镜还响——成片里的表现是「有人在画外乱说话」",
-        "description": "查**无台词镜里的异常发声**:本该沉默的反应镜,音轨却比同场说话镜还响——成片里的表现是「有人在画外乱说话」。免费。\n★用在**原声剧**上(use_clip_audio=true,即直接用 AI 视频自带声音那种)。走 TTS 配音的片子不会有这个问题。\n★**很慢**:每镜要完整解码音轨,实测 6~10 秒/镜(后端限并发 4),整集几十镜要等几分钟。别在产线中途反复调,放在成片前查一次。\n★shots_probe_failed 是**没测成**的镜数,不代表那些镜有问题。",
+        "description": "查**无台词镜里的异常发声**:本该沉默的反应镜,音轨却比同场说话镜还响——成片里的表现是「有人在画外乱说话」。免费。\n★用在**原声剧**上(use_clip_audio=true,即直接用 AI 视频自带声音那种)。走 TTS 配音的片子不会有这个问题。\n★**很慢**:每镜要完整解码音轨,实测 6~10 秒/镜(后端限并发 4),整集几十镜要等几分钟。别在产线中途反复调,放在成片前查一次。\n★shots_probe_failed 是**没测成**的镜数,不代表那些镜有问题。\n★★probe_speech:true 再对**台词栏为空**的镜跑人声检测(已标定判据):厂商在无台词镜里自己念出一句话时,响度比测不出来,这个能——命中的镜列在 unexpected_speech,text 是念出的内容。更慢(每镜下载+转写),一次最多 20 镜,skipped_by_limit 是剩下的、再调一次接着扫。只报不改:由客户决定 mute_only 静掉还是重生成。",
         "tags": [
           "episodes"
         ],
@@ -6854,6 +6854,14 @@
               "type": "integer",
               "exclusiveMinimum": 0
             }
+          },
+          {
+            "name": "probe_speech",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "type": "string"
+            }
           }
         ],
         "responses": {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@starreel/mcp",
-  "version": "0.1.112",
+  "version": "0.1.113",
   "mcpName": "ai.starreel/starreel",
   "description": "StarReel MCP server — drive the AI short-drama production pipeline (script → storyboards → frames → video → final cut) from Claude, Cursor, or any MCP client",
   "license": "MIT",

package/server.json

@@ -2,13 +2,13 @@
   "$schema": "https://static.modelcontextprotocol.io/schemas/2025-09-29/server.schema.json",
   "name": "ai.starreel/starreel",
   "description": "Turn a script into a finished, downloadable short-drama episode — via MCP or REST.",
-  "version": "0.1.112",
+  "version": "0.1.113",
   "websiteUrl": "https://starreel.ai",
   "packages": [
     {
       "registryType": "npm",
       "identifier": "@starreel/mcp",
-      "version": "0.1.112",
+      "version": "0.1.113",
       "transport": {
         "type": "stdio"
       },