@starreel/mcp 0.1.133 → 0.1.134

package/SKILL.md

@@ -1108,8 +1108,10 @@ to close") tells the vendor to fit that entire sequence into each 3-second shot.
 - **Mix** (free; settings only — `compose_episode` again to hear them, `rerender_episode`
   reuses the old timeline): whole drama via `update_project_settings`
   (`bgm_volume_preset` / `bgm_volume_db` / `lufs_target`); one episode via
-  `set_episode_audio`; one music section's level and fades via `list_bgm_cues` →
-  `update_bgm_cue`. Don't download the cut to re-mix it locally.
+  `set_episode_audio` (music level, plus `clip_audio_gain_db` for the clips' own sound and
+  `voice_gain_db` for the TTS dialogue + narration track); one music section's level, fades,
+  where in the track it starts (`track_offset_ms`) and how late after its first shot it comes in
+  (`start_shift_ms`) via `list_bgm_cues` → `update_bgm_cue`. Don't download the cut to re-mix it locally.
 - **Finish**: `compose_episode`, `get_final_cut`, `get_export`,
   `generate_episode_poster`, `generate_cover`
 - **What did this drama cost?** `get_drama_bill` — per kind `charged` / `refunded`

package/dist/tools/produce.js

@@ -1511,24 +1511,35 @@ export function registerProduceTools(server, client) {
     server.tool('get_bgm_plan', '查本集配乐会分成几幕(免费、只读、不生成):每幕的幕号 act、覆盖镜号 sb_from~sb_to、时长、平均情绪强度。' +
         '要用 generate_bgm 的 director.acts 按幕锁定参数时,先调这个拿幕号。' +
         '★这是独立的只读工具:看分幕**不要**去调 generate_bgm——那个一调就是扣费生成。', { episode_id: z.number().int().positive() }, async ({ episode_id }) => jsonResult(await client.produceGet(`/episodes/${episode_id}/bgm-plan`)));
-    server.tool('set_episode_audio', '设置**本集**配乐音量(覆盖整剧设定,免费)。整剧统一的用 update_project_settings。' +
+    server.tool('set_episode_audio', '设置**本集**成片混音(免费):配乐音量(覆盖整剧设定)、片段原声增益、配音轨增益。整剧统一的配乐音量用 update_project_settings。' +
         '★只改设置:成片要 compose_episode 重新合成才变(rerender_episode 用旧时间线,不带上)。' +
-        '★想调某一段配乐的音量或淡入淡出,用 list_bgm_cues + update_bgm_cue。', {
+        '★想调某一段配乐的音量、淡入淡出或起点,用 list_bgm_cues + update_bgm_cue。' +
+        '★原声=视频片段自带的声音(原声剧里就是角色台词);配音轨=TTS 生成的对白与旁白(两者在同一轨里预混,只能整轨调,分不开)。' +
+        '★本集若走逐镜合成片终拼(每镜都有合成片),配音已烤进每镜、与原声是同一条音频,这两个增益不生效——响应里会有 warning,照实转告客户。', {
         episode_id: z.number().int().positive(),
         bgm_volume_preset: z.enum(['off', 'low', 'auto', 'high', 'inherit']).optional()
             .describe('本集配乐音量档:off静音/low轻(-28dB)/auto自适应/high强(-16dB)/inherit跟随整剧'),
         bgm_volume_db: z.number().min(-60).max(0).nullable().optional()
             .describe('本集自定义配乐音量(dB,-60~0),覆盖档位并关自适应;null=清除、跟随整剧'),
+        clip_audio_gain_db: z.number().min(-30).max(6).nullable().optional()
+            .describe('片段原声比系统默认响/轻多少(dB,-30~+6;0=默认);原声剧台词听不清→调高,环境噪音太吵→调低;null=清回默认'),
+        voice_gain_db: z.number().min(-24).max(6).nullable().optional()
+            .describe('配音轨(TTS 对白与旁白)比系统默认响/轻多少(dB,-24~+6;0=默认);null=清回默认'),
     }, async ({ episode_id, ...rest }) => jsonResult(await client.producePut(`/episodes/${episode_id}/audio`, rest)));
-    server.tool('list_bgm_cues', '列出本集的配乐段(AI 配乐按情绪分幕,每段覆盖一段镜号 sb_from~sb_to):id、覆盖范围、gain_db(null=跟随音量档)、fade_in_ms / fade_out_ms。' +
+    server.tool('list_bgm_cues', '列出本集的配乐段(AI 配乐按情绪分幕,每段覆盖一段镜号 sb_from~sb_to):id、覆盖范围、gain_db(null=跟随音量档)、fade_in_ms / fade_out_ms、track_offset_ms / start_shift_ms(null=系统决定)。' +
         'episode_id 为 null 的是**整剧共用段**,改它会影响所有集。免费。', { episode_id: z.number().int().positive() }, async ({ episode_id }) => jsonResult(await client.produceGet(`/episodes/${episode_id}/bgm-cues`)));
-    server.tool('update_bgm_cue', '调某一段配乐的音量与淡入淡出(免费)。只改这三项;换曲目或改覆盖范围用 generate_bgm 重新生成。' +
-        '★例:配乐进得太突兀→加大 fade_in_ms;某段压对白→降 gain_db。改完 compose_episode 重新合成才生效。', {
+    server.tool('update_bgm_cue', '调某一段配乐的音量、淡入淡出与起点(免费)。换曲目或改覆盖镜号范围用 generate_bgm 重新生成。' +
+        '★例:配乐进得太突兀→加大 fade_in_ms;某段压对白→降 gain_db;想从曲子的高潮部分开始→设 track_offset_ms;' +
+        '想等这段第一镜开口之后再进→设 start_shift_ms。改完 compose_episode 重新合成才生效。', {
         episode_id: z.number().int().positive(),
         cue_id: z.number().int().positive().describe('来自 list_bgm_cues'),
         gain_db: z.number().min(-60).max(0).nullable().optional().describe('这段配乐的音量(dB,-60~0),设了就覆盖音量档;null=恢复跟随本集/整剧音量档'),
         fade_in_ms: z.number().int().min(0).max(15000).optional().describe('淡入毫秒(整数,0~15000)'),
         fade_out_ms: z.number().int().min(0).max(15000).optional().describe('淡出毫秒(整数,0~15000)'),
+        track_offset_ms: z.number().int().min(0).max(600000).nullable().optional()
+            .describe('从配乐文件第几毫秒开始播(0~600000),覆盖系统自动挑的切入点;超过曲长会钳到曲尾前 1 秒;null=交回系统自动挑'),
+        start_shift_ms: z.number().int().min(0).max(60000).nullable().optional()
+            .describe('这段配乐在它第一镜开始后再晚多少毫秒进(0~60000);默认卡在第一镜起点。段尾不变,至少留 1 秒;null=不平移'),
     }, async ({ episode_id, cue_id, ...rest }) => jsonResult(await client.producePut(`/episodes/${episode_id}/bgm-cues/${cue_id}`, rest)));
     server.tool('get_bgm_prompt_guide', '取「AI 配乐提示词」的书写规范:两个档位怎么选、该写哪些维度(附可照抄的示例)、' +
         '哪些是写了也不会生效的硬限制(纯器乐/时长/不做音效/不复刻具体曲目)、常见写坏的方式。' +

package/openapi.json

@@ -2,8 +2,8 @@
   "openapi": "3.1.0",
   "info": {
     "title": "StarReel Production API",
-    "version": "0.1.133",
-    "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 v0.1.133 tool surface (operationIds match MCP tool names 1:1)."
+    "version": "0.1.134",
+    "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 v0.1.134 tool surface (operationIds match MCP tool names 1:1)."
   },
   "servers": [
     {
@@ -3475,8 +3475,8 @@
     "/episodes/{episode_id}/audio": {
       "put": {
         "operationId": "set_episode_audio",
-        "summary": "设置**本集**配乐音量(覆盖整剧设定,免费)",
-        "description": "设置**本集**配乐音量(覆盖整剧设定,免费)。整剧统一的用 update_project_settings。★只改设置:成片要 compose_episode 重新合成才变(rerender_episode 用旧时间线,不带上)。★想调某一段配乐的音量或淡入淡出,用 list_bgm_cues + update_bgm_cue。",
+        "summary": "设置**本集**成片混音(免费):配乐音量(覆盖整剧设定)、片段原声增益、配音轨增益",
+        "description": "设置**本集**成片混音(免费):配乐音量(覆盖整剧设定)、片段原声增益、配音轨增益。整剧统一的配乐音量用 update_project_settings。★只改设置:成片要 compose_episode 重新合成才变(rerender_episode 用旧时间线,不带上)。★想调某一段配乐的音量、淡入淡出或起点,用 list_bgm_cues + update_bgm_cue。★原声=视频片段自带的声音(原声剧里就是角色台词);配音轨=TTS 生成的对白与旁白(两者在同一轨里预混,只能整轨调,分不开)。★本集若走逐镜合成片终拼(每镜都有合成片),配音已烤进每镜、与原声是同一条音频,这两个增益不生效——响应里会有 warning,照实转告客户。",
         "tags": [
           "episodes"
         ],
@@ -3519,6 +3519,30 @@
                         "type": "null"
                       }
                     ]
+                  },
+                  "clip_audio_gain_db": {
+                    "anyOf": [
+                      {
+                        "type": "number",
+                        "minimum": -30,
+                        "maximum": 6
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
+                  },
+                  "voice_gain_db": {
+                    "anyOf": [
+                      {
+                        "type": "number",
+                        "minimum": -24,
+                        "maximum": 6
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
                   }
                 }
               }
@@ -3823,8 +3847,8 @@
     "/episodes/{episode_id}/bgm-cues": {
       "get": {
         "operationId": "list_bgm_cues",
-        "summary": "列出本集的配乐段(AI 配乐按情绪分幕,每段覆盖一段镜号 sb_from~sb_to):id、覆盖范围、gain_db(null=跟随音量档)、fade_in_ms / fade_out_ms",
-        "description": "列出本集的配乐段(AI 配乐按情绪分幕,每段覆盖一段镜号 sb_from~sb_to):id、覆盖范围、gain_db(null=跟随音量档)、fade_in_ms / fade_out_ms。episode_id 为 null 的是**整剧共用段**,改它会影响所有集。免费。",
+        "summary": "列出本集的配乐段(AI 配乐按情绪分幕,每段覆盖一段镜号 sb_from~sb_to):id、覆盖范围、gain_db(null=跟随音量档)、fade_in_ms / fade_out_ms、track_offset_ms / start",
+        "description": "列出本集的配乐段(AI 配乐按情绪分幕,每段覆盖一段镜号 sb_from~sb_to):id、覆盖范围、gain_db(null=跟随音量档)、fade_in_ms / fade_out_ms、track_offset_ms / start_shift_ms(null=系统决定)。episode_id 为 null 的是**整剧共用段**,改它会影响所有集。免费。",
         "tags": [
           "episodes"
         ],
@@ -3870,8 +3894,8 @@
     "/episodes/{episode_id}/bgm-cues/{cue_id}": {
       "put": {
         "operationId": "update_bgm_cue",
-        "summary": "调某一段配乐的音量与淡入淡出(免费)",
-        "description": "调某一段配乐的音量与淡入淡出(免费)。只改这三项;换曲目或改覆盖范围用 generate_bgm 重新生成。★例:配乐进得太突兀→加大 fade_in_ms;某段压对白→降 gain_db。改完 compose_episode 重新合成才生效。",
+        "summary": "调某一段配乐的音量、淡入淡出与起点(免费)",
+        "description": "调某一段配乐的音量、淡入淡出与起点(免费)。换曲目或改覆盖镜号范围用 generate_bgm 重新生成。★例:配乐进得太突兀→加大 fade_in_ms;某段压对白→降 gain_db;想从曲子的高潮部分开始→设 track_offset_ms;想等这段第一镜开口之后再进→设 start_shift_ms。改完 compose_episode 重新合成才生效。",
         "tags": [
           "episodes"
         ],
@@ -3924,6 +3948,30 @@
                     "type": "integer",
                     "minimum": 0,
                     "maximum": 15000
+                  },
+                  "track_offset_ms": {
+                    "anyOf": [
+                      {
+                        "type": "integer",
+                        "minimum": 0,
+                        "maximum": 600000
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
+                  },
+                  "start_shift_ms": {
+                    "anyOf": [
+                      {
+                        "type": "integer",
+                        "minimum": 0,
+                        "maximum": 60000
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ]
                   }
                 }
               }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@starreel/mcp",
-  "version": "0.1.133",
+  "version": "0.1.134",
   "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": "0.1.133",
+  "version": "0.1.134",
   "websiteUrl": "https://starreel.ai",
   "packages": [
     {
       "registryType": "npm",
       "identifier": "@starreel/mcp",
-      "version": "0.1.133",
+      "version": "0.1.134",
       "transport": {
         "type": "stdio"
       },