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

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_minimax_voice_id()
+    return _choose_azure_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:
-    path = AZURE_TTS_PATH if AZURE_TTS_PATH.startswith("/") else f"/{AZURE_TTS_PATH}"
+def _azure_tts_url_for(path_value: str) -> str:
+    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(
-        _azure_tts_url(),
-        headers={
-            "Authorization": f"Bearer {AZURE_OPENAI_API_KEY}",
-            "api-key": AZURE_OPENAI_API_KEY,
-            "Content-Type": "application/json",
-        },
-        json=payload,
-        timeout=120,
-    )
+    headers = {
+        "Authorization": f"Bearer {AZURE_OPENAI_API_KEY}",
+        "api-key": AZURE_OPENAI_API_KEY,
+        "Content-Type": "application/json",
+    }
+    resp: httpx.Response | None = None
+    errors: list[str] = []
+    with ai_http_client(timeout=120) as client:
+        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 _minimax_tts_sync(job_id, text, voice_id, target_seconds), "minimax", MINIMAX_TTS_MODEL
+    return _azure_openai_tts_sync(job_id, text, voice_id, target_seconds), "azure_openai", AZURE_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_model = AZURE_TTS_MODEL if voice_provider == "azure_openai" else MINIMAX_TTS_MODEL
+    voice_provider = "azure_openai"
+    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_tts": AZURE_TTS_MODEL if VOICE_PROVIDER == "azure_openai" else MINIMAX_TTS_MODEL,
-            "voice_id": AZURE_TTS_VOICE_ID if VOICE_PROVIDER == "azure_openai" else MINIMAX_TTS_VOICE_ID,
-            "voice_pool": AZURE_TTS_VOICE_POOL if VOICE_PROVIDER == "azure_openai" else (MINIMAX_TTS_VOICE_POOL or [MINIMAX_TTS_VOICE_ID]),
-            "voice_configured": bool(AZURE_OPENAI_API_KEY) if VOICE_PROVIDER == "azure_openai" else bool(MINIMAX_API_KEY),
-            "minimax_tts": MINIMAX_TTS_MODEL,
-            "minimax_voice": MINIMAX_TTS_VOICE_ID,
-            "minimax_voice_pool": MINIMAX_TTS_VOICE_POOL or [MINIMAX_TTS_VOICE_ID],
-            "minimax_configured": bool(MINIMAX_API_KEY),
+            "voice_base_url": AZURE_OPENAI_BASE_URL,
+            "voice_tts": AZURE_TTS_MODEL,
+            "voice_tts_paths": AZURE_TTS_PATHS,
+            "voice_id": AZURE_TTS_VOICE_ID,
+            "voice_pool": AZURE_TTS_VOICE_POOL,
+            "voice_configured": bool(AZURE_OPENAI_API_KEY),
+            "minimax_disabled": True,
             "video": VIDEO_MODEL,
             "video_aliases": VIDEO_MODEL_ALIASES,
             "video_provider": video_provider_name(),