auto-save 2026-05-18 14:46 (~7)

RULES.md

@@ -65,12 +65,10 @@
 - `IMAGE_BASE_URL` / `IMAGE_API_KEY` / `IMAGE_MODEL`：OpenAI 兼容生图网关；当前所有生图入口一律强制使用 `gpt-image-2`，不做其他图片模型 fallback
 - `GPT_IMAGE_MODEL` / `SUBJECT_ASSET_IMAGE_MODEL` / `SUBJECT_ASSET_IMAGE_MODELS`：保留兼容旧环境变量名，但服务端会强制主体 6 视图和所有其他生图入口都只使用 `gpt-image-2`
 - `AI_HTTP_PROXY` / `IMAGE_HTTP_PROXY`：可选的 AI 网关出站代理；本地 launchd 后台进程不一定继承 shell 的 `http_proxy/https_proxy`，如生图报 DNS / ConnectError，可在本地 `api/.env` 配置后重启后端。`/health` 只回传是否配置代理，不回传代理地址。
-- `VOICE_PROVIDER`：配音通道，当前固定使用 `azure_openai`
+- `VOICE_PROVIDER`：配音通道，服务端固定使用 `azure_openai`；旧环境若写 `minimax` 会被忽略
 - `AZURE_OPENAI_BASE_URL` / `AZURE_OPENAI_API_KEY`：微软 Azure OpenAI 协议配音网关；本地未单独配置 Key 时回退复用 `LLM_API_KEY`
-- `AZURE_TTS_MODEL` / `AZURE_TTS_VOICE_ID` / `AZURE_TTS_VOICE_POOL` / `AZURE_TTS_PATH`：Azure OpenAI TTS 模型、默认音色、音色池和 OpenAI 协议语音路径
+- `AZURE_TTS_MODEL` / `AZURE_TTS_VOICE_ID` / `AZURE_TTS_VOICE_POOL` / `AZURE_TTS_PATH` / `AZURE_TTS_PATHS`：Azure OpenAI TTS 模型、默认音色、音色池和 OpenAI 协议语音路径；后端会按 `AZURE_TTS_PATHS` 依次尝试，便于区分路径不对和整条语音服务不可用
-- `MINIMAX_API_KEY`：MiniMax T2A 配音 Key，只能放本地 `api/.env`，不能入库；当前第一步暂不默认调用
+- MiniMax TTS 不再作为语音 fallback；不要新增或依赖 `MINIMAX_*` 配置
-- `MINIMAX_TTS_BASE_URL` / `MINIMAX_TTS_MODEL` / `MINIMAX_TTS_VOICE_ID`：MiniMax 旧配音端点、模型和兜底音色配置，仅作为保留兼容；当前不作为默认语音通道
-- `MINIMAX_TTS_VOICE_POOL`：MiniMax 英文随机音色池；当前默认男声 `English_magnetic_voiced_man`、女声 `English_Upbeat_Woman`、成熟声 `English_MaturePartner`，供后续新配音阶段使用
 - `POE_API_KEY` / `VIDEO_API_KEY`：视频生成通道 Key，只能放本地环境变量
 - `WEB_AUTH_USERNAME` / `WEB_AUTH_PASSWORD` / `WEB_AUTH_SESSION_SECRET`：生产网页登录和会话签名配置；密码和 session secret 只放服务器环境变量，不入库
 - `FFMPEG_BIN` / `FFPROBE_BIN`：可选本地媒体二进制路径；本机 Homebrew ffmpeg 动态库损坏时，后端会自动跳过不可用的 PATH 版本并尝试本机静态 ffmpeg 备选，生产仍建议使用系统 ffmpeg/ffprobe

api/.env.example

@@ -37,6 +37,7 @@ VIDEO_MODEL_VEO3=veo-3.1-fast
 # 音频文案改写 + Azure OpenAI 配音
 AUDIO_REWRITE_MODEL=gpt-4o
 AUDIO_PRODUCT_BRIEF="SKG 智能按摩产品，主打日常肩颈、腰背、眼部、膝盖或足部放松；广告表达要高级、干净、可信，不做医疗疗效承诺。"
+# 语音通道服务端固定为 azure_openai；旧 VOICE_PROVIDER=minimax 会被忽略。
 VOICE_PROVIDER=azure_openai
 AZURE_OPENAI_BASE_URL=https://ai.skg.com/azure
 AZURE_OPENAI_API_KEY=
@@ -44,13 +45,7 @@ AZURE_TTS_MODEL=gpt-4o-mini-tts
 AZURE_TTS_VOICE_ID=alloy
 AZURE_TTS_VOICE_POOL=alloy,verse,shimmer
 AZURE_TTS_PATH=/audio/speech
-
+AZURE_TTS_PATHS=/audio/speech,/v1/audio/speech
-# MiniMax 旧配音通道，保留兼容；默认不走
-MINIMAX_API_KEY=
-MINIMAX_TTS_BASE_URL=https://api.minimax.io
-MINIMAX_TTS_MODEL=speech-2.8-turbo
-MINIMAX_TTS_VOICE_ID=English_expressive_narrator
-MINIMAX_TTS_VOICE_POOL=English_magnetic_voiced_man,English_Upbeat_Woman,English_MaturePartner
 
 # Poe 视频 API（优先用于 Seedance / Kling / Veo）
 POE_API_BASE_URL=https://api.poe.com/v1

api/main.py

@@ -105,7 +105,9 @@ MINIMAX_TTS_VOICE_POOL = [
     for v in os.getenv("MINIMAX_TTS_VOICE_POOL", ",".join(DEFAULT_MINIMAX_TTS_VOICE_POOL)).split(",")
     if v.strip()
 ]
-VOICE_PROVIDER = os.getenv("VOICE_PROVIDER", "azure_openai").strip().lower() or "azure_openai"
+# Voice is intentionally fixed to Azure OpenAI. Older envs may still contain
+# VOICE_PROVIDER=minimax, but the runtime must not fall back to MiniMax.
+VOICE_PROVIDER = "azure_openai"
 AZURE_OPENAI_BASE_URL = os.getenv("AZURE_OPENAI_BASE_URL", "https://ai.skg.com/azure").strip().rstrip("/")
 AZURE_OPENAI_API_KEY = os.getenv("AZURE_OPENAI_API_KEY", LLM_API_KEY).strip()
 AZURE_TTS_MODEL = os.getenv("AZURE_TTS_MODEL", "gpt-4o-mini-tts").strip() or "gpt-4o-mini-tts"
@@ -117,6 +119,11 @@ AZURE_TTS_VOICE_POOL = [
     if v.strip()
 ]
 AZURE_TTS_PATH = os.getenv("AZURE_TTS_PATH", "/audio/speech").strip() or "/audio/speech"
+AZURE_TTS_PATHS = [
+    p.strip()
+    for p in os.getenv("AZURE_TTS_PATHS", f"{AZURE_TTS_PATH},/audio/speech,/v1/audio/speech").split(",")
+    if p.strip()
+]
 
 POE_API_BASE_URL = os.getenv("POE_API_BASE_URL", "https://api.poe.com/v1").strip() or "https://api.poe.com/v1"
 POE_API_KEY = os.getenv("POE_API_KEY", "").strip()
@@ -2334,9 +2341,7 @@ def _choose_azure_voice_id() -> str:
 
 
 def _choose_tts_voice_id() -> str:
-    if VOICE_PROVIDER == "azure_openai":
+    return _choose_azure_voice_id()
-        return _choose_azure_voice_id()
-    return _choose_minimax_voice_id()
 
 
 def _voice_speed_for(voice_id: str, target_seconds: float, text: str) -> float:
@@ -2400,13 +2405,22 @@ def _minimax_tts_sync(job_id: str, text: str, voice_id: str, target_seconds: flo
     return f"/jobs/{job_id}/audio-script.mp3"
 
 
-def _azure_tts_url() -> str:
+def _azure_tts_url_for(path_value: str) -> str:
-    path = AZURE_TTS_PATH if AZURE_TTS_PATH.startswith("/") else f"/{AZURE_TTS_PATH}"
+    path = path_value if path_value.startswith("/") else f"/{path_value}"
     if AZURE_OPENAI_BASE_URL.endswith(path):
         return AZURE_OPENAI_BASE_URL
     return f"{AZURE_OPENAI_BASE_URL}{path}"
 
 
+def _azure_tts_urls() -> list[str]:
+    urls: list[str] = []
+    for path in AZURE_TTS_PATHS or [AZURE_TTS_PATH]:
+        url = _azure_tts_url_for(path)
+        if url not in urls:
+            urls.append(url)
+    return urls
+
+
 def _azure_openai_tts_sync(job_id: str, text: str, voice_id: str, target_seconds: float = 12.0) -> str:
     if not AZURE_OPENAI_API_KEY:
         raise RuntimeError("AZURE_OPENAI_API_KEY 或 LLM_API_KEY 未配置，未生成配音")
@@ -2419,18 +2433,32 @@ def _azure_openai_tts_sync(job_id: str, text: str, voice_id: str, target_seconds
         "response_format": "mp3",
         "speed": _voice_speed_for(voice_id, target_seconds, text),
     }
-    resp = httpx.post(
+    headers = {
-        _azure_tts_url(),
+        "Authorization": f"Bearer {AZURE_OPENAI_API_KEY}",
-        headers={
+        "api-key": AZURE_OPENAI_API_KEY,
-            "Authorization": f"Bearer {AZURE_OPENAI_API_KEY}",
+        "Content-Type": "application/json",
-            "api-key": AZURE_OPENAI_API_KEY,
+    }
-            "Content-Type": "application/json",
+    resp: httpx.Response | None = None
-        },
+    errors: list[str] = []
-        json=payload,
+    with ai_http_client(timeout=120) as client:
-        timeout=120,
+        for url in _azure_tts_urls():
-    )
+            try:
+                current = client.post(url, headers=headers, json=payload)
+            except Exception as e:
+                errors.append(f"{url}: {type(e).__name__}: {e}")
+                continue
+            if current.status_code < 400:
+                resp = current
+                break
+            errors.append(f"{url}: HTTP {current.status_code}: {current.text[:180]}")
+            if current.status_code not in {404, 405}:
+                resp = current
+                break
+    if resp is None:
+        raise RuntimeError("Azure OpenAI TTS 不可用；已尝试 " + " | ".join(errors))
     if resp.status_code >= 400:
-        raise RuntimeError(f"Azure OpenAI TTS HTTP {resp.status_code}: {resp.text[:300]}")
+        detail = " | ".join(errors) or resp.text[:300]
+        raise RuntimeError(f"Azure OpenAI TTS HTTP {resp.status_code}: {detail[:600]}")
     audio_bytes = resp.content
     if not audio_bytes:
         raise RuntimeError("Azure OpenAI TTS 未返回音频内容")
@@ -2447,9 +2475,7 @@ def _azure_openai_tts_sync(job_id: str, text: str, voice_id: str, target_seconds
 
 
 def _tts_sync(job_id: str, text: str, voice_id: str, target_seconds: float = 12.0) -> tuple[str, str, str]:
-    if VOICE_PROVIDER == "azure_openai":
+    return _azure_openai_tts_sync(job_id, text, voice_id, target_seconds), "azure_openai", AZURE_TTS_MODEL
-        return _azure_openai_tts_sync(job_id, text, voice_id, target_seconds), "azure_openai", AZURE_TTS_MODEL
-    return _minimax_tts_sync(job_id, text, voice_id, target_seconds), "minimax", MINIMAX_TTS_MODEL
 
 
 def _build_audio_script_sync(job_id: str, segments: list[TranscriptSegment], target_seconds: float = 12.0) -> AudioScript:
@@ -2461,8 +2487,8 @@ def _build_audio_script_sync(job_id: str, segments: list[TranscriptSegment], tar
     speaker_profile, rhythm_profile = _audio_delivery_profile(segments, duration, selected_voice_id)
     voice_url = ""
     voice_error = ""
-    voice_provider = "azure_openai" if VOICE_PROVIDER == "azure_openai" else "minimax"
+    voice_provider = "azure_openai"
-    voice_model = AZURE_TTS_MODEL if voice_provider == "azure_openai" else MINIMAX_TTS_MODEL
+    voice_model = AZURE_TTS_MODEL
     try:
         voice_url, voice_provider, voice_model = _tts_sync(job_id, rewritten, selected_voice_id, duration)
     except Exception as e:
@@ -3060,7 +3086,7 @@ def health() -> dict:
         "auth_configured": WEB_AUTH_CONFIGURED,
         "base_url": LLM_BASE_URL or "openai-default",
         "image_base_url": IMAGE_BASE_URL or LLM_BASE_URL or "openai-default",
-        "voice_base_url": AZURE_OPENAI_BASE_URL if VOICE_PROVIDER == "azure_openai" else MINIMAX_TTS_BASE_URL,
+        "voice_base_url": AZURE_OPENAI_BASE_URL,
         "models": {
             "asr": ASR_MODEL,
             "local_asr": LOCAL_ASR_MODEL,
@@ -3077,15 +3103,13 @@ def health() -> dict:
             "subject_image": SUBJECT_ASSET_IMAGE_MODEL,
             "subject_image_fallbacks": SUBJECT_ASSET_IMAGE_MODELS,
             "voice_provider": VOICE_PROVIDER,
-            "voice_base_url": AZURE_OPENAI_BASE_URL if VOICE_PROVIDER == "azure_openai" else MINIMAX_TTS_BASE_URL,
+            "voice_base_url": AZURE_OPENAI_BASE_URL,
-            "voice_tts": AZURE_TTS_MODEL if VOICE_PROVIDER == "azure_openai" else MINIMAX_TTS_MODEL,
+            "voice_tts": AZURE_TTS_MODEL,
-            "voice_id": AZURE_TTS_VOICE_ID if VOICE_PROVIDER == "azure_openai" else MINIMAX_TTS_VOICE_ID,
+            "voice_tts_paths": AZURE_TTS_PATHS,
-            "voice_pool": AZURE_TTS_VOICE_POOL if VOICE_PROVIDER == "azure_openai" else (MINIMAX_TTS_VOICE_POOL or [MINIMAX_TTS_VOICE_ID]),
+            "voice_id": AZURE_TTS_VOICE_ID,
-            "voice_configured": bool(AZURE_OPENAI_API_KEY) if VOICE_PROVIDER == "azure_openai" else bool(MINIMAX_API_KEY),
+            "voice_pool": AZURE_TTS_VOICE_POOL,
-            "minimax_tts": MINIMAX_TTS_MODEL,
+            "voice_configured": bool(AZURE_OPENAI_API_KEY),
-            "minimax_voice": MINIMAX_TTS_VOICE_ID,
+            "minimax_disabled": True,
-            "minimax_voice_pool": MINIMAX_TTS_VOICE_POOL or [MINIMAX_TTS_VOICE_ID],
-            "minimax_configured": bool(MINIMAX_API_KEY),
             "video": VIDEO_MODEL,
             "video_aliases": VIDEO_MODEL_ALIASES,
             "video_provider": video_provider_name(),

deploy/.env.production.example

@@ -38,6 +38,7 @@ AI_HTTP_PROXY=
 # Audio rewrite and Azure OpenAI TTS
 AUDIO_REWRITE_MODEL=gpt-4o
 AUDIO_PRODUCT_BRIEF="SKG smart massage products for daily neck, shoulder, back, eye, knee, and foot relaxation. Keep claims premium, clean, credible, and non-medical."
+# Voice is fixed to Azure OpenAI in the backend; legacy VOICE_PROVIDER=minimax is ignored.
 VOICE_PROVIDER=azure_openai
 AZURE_OPENAI_BASE_URL=https://ai.skg.com/azure
 AZURE_OPENAI_API_KEY=
@@ -45,13 +46,7 @@ AZURE_TTS_MODEL=gpt-4o-mini-tts
 AZURE_TTS_VOICE_ID=alloy
 AZURE_TTS_VOICE_POOL=alloy,verse,shimmer
 AZURE_TTS_PATH=/audio/speech
-
+AZURE_TTS_PATHS=/audio/speech,/v1/audio/speech
-# Legacy MiniMax TTS fallback; not the default voice provider.
-MINIMAX_API_KEY=
-MINIMAX_TTS_BASE_URL=https://api.minimax.io
-MINIMAX_TTS_MODEL=speech-2.8-turbo
-MINIMAX_TTS_VOICE_ID=English_expressive_narrator
-MINIMAX_TTS_VOICE_POOL=English_magnetic_voiced_man,English_Upbeat_Woman,English_MaturePartner
 
 # Video generation. Use SKG Doubao / Seedance gateway in production.
 POE_API_BASE_URL=https://api.poe.com/v1

web/components/dashboard.tsx

@@ -641,15 +641,15 @@ export const Dashboard = forwardRef<DashboardHandle, Props>(function Dashboard({
                   </div>
                 </KanbanCard>
 
-                <KanbanCard tone="green" tags={["配音"]} title={job?.audio_script?.voice_model || "MiniMax T2A"}>
+                <KanbanCard tone="green" tags={["配音"]} title={job?.audio_script?.voice_model || "Azure OpenAI TTS"}>
                   {job?.audio_script?.voice_url ? (
                     <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 MiniMax 后自动生成配音文件"}
+                      {job?.audio_script?.error || "配置 Azure OpenAI TTS 后自动生成配音文件"}
                     </div>
                   )}
-                  <div className="kanban-meta">{job?.audio_script?.voice_id || "random English voice"}</div>
+                  <div className="kanban-meta">{job?.audio_script?.voice_id || "Azure voice"}</div>
                 </KanbanCard>
               </>
             )}

web/components/nodes/index.tsx

@@ -2102,7 +2102,7 @@ export function RewriteNode({ data, selected }: any) {
 }
 
 /* ============================================================
-   5b. AudioNode — 合并 ASR + 翻译 + 改写 + MiniMax 配音
+   5b. AudioNode — 合并 ASR + 翻译 + 改写 + Azure OpenAI 配音
    ============================================================ */
 export function AudioNode({ data, selected }: any) {
   const d: NodeData = data
@@ -2152,9 +2152,9 @@ export function AudioNode({ data, selected }: any) {
         }}
       >
         <div>
-          音轨 → 取时长/节奏 → SKG 英文产品口播 → MiniMax 随机英文配音<br />
+          音轨 → 取时长/节奏 → SKG 英文产品口播 → Azure OpenAI 英文配音<br />
           <span className="text-[var(--text-faint)] font-mono">
-            {audioScript?.rewrite_model || "AUDIO_REWRITE_MODEL"} → {audioScript?.voice_model || "MiniMax T2A"}
+            {audioScript?.rewrite_model || "AUDIO_REWRITE_MODEL"} → {audioScript?.voice_model || "Azure OpenAI TTS"}
           </span>
         </div>
         {job && (
@@ -2195,7 +2195,7 @@ export function AudioNode({ data, selected }: any) {
             )}
           </div>
         )}
-        {voiceUrl && <div className="text-[10.5px] text-emerald-200/85">MiniMax natural English voice ready · 底部音频条播放</div>}
+        {voiceUrl && <div className="text-[10.5px] text-emerald-200/85">Azure OpenAI English voice ready · 底部音频条播放</div>}
         {isRewriting && (
           <div className="text-[10.5px] text-[var(--text-faint)]">正在按原音频时长生成英文产品口播和配音…</div>
         )}

web/lib/api.ts

@@ -172,10 +172,8 @@ export interface RuntimeModels {
   voice_id?: string
   voice_pool?: string[]
   voice_configured?: boolean
-  minimax_tts?: string
+  voice_tts_paths?: string[]
-  minimax_voice?: string
+  minimax_disabled?: boolean
-  minimax_voice_pool?: string[]
-  minimax_configured?: boolean
   video?: string
   video_aliases?: Record<string, string>
   video_provider?: string
@@ -601,9 +599,8 @@ export interface BackendHealth {
     translate?: string
     rewrite?: string
     audio_rewrite?: string
-    minimax_tts?: string
+    voice_tts_paths?: string[]
-    minimax_voice?: string
+    minimax_disabled?: boolean
-    minimax_configured?: boolean
     video?: string
     video_aliases?: Record<string, string>
     video_base_url?: string