chat: fix and complete voice chat (STT/TTS) wiring — full endpoint URLs, live gateway key, engine defaults

The speech section shipped 6 Nov was doubly broken: LibreChat POSTs to
speech.*.openai.url VERBATIM in 0.8.8, so the base '/v1' URL 404'd, and the
STT_API_KEY/TTS_API_KEY env values held a key that no longer exists on the
gateway (401 token_not_found). Also:
- STT: tinfoil/voxtral-small-24b (token-priced; gateway bills ~$0.00008/request,
  125x under the flat $0.01/request whisper; same TEE provider, verified equal
  quality on dictation clips). Whisper remains allowed on the key as fallback.
- TTS voices: full provider speaker list (an unknown voice 400s at the gateway).
- speechTab: object form seeds Settings->Speech defaults (engineSTT/engineTTS
  external, voice casual_female) for members who never saved their own.
- new gateway key: alias librechat-speech, $5/30d, audio models only, injected
  as STT_API_KEY/TTS_API_KEY app env.

Verified on a throwaway librechat-test install then live (chat.inference.coop):
config/get serves the defaults; /api/files/speech/stt returns a correct
transcript; /api/files/speech/tts/manual returns audio. Known gap (gateway-side,
NOT this repo): aspeech rows log $0 spend — voxtral-tts is unmetered on the
gateway's aspeech path while the co-op pays ~$0.002/request.

CloudronManifest.json

@@ -1,59 +1,59 @@
 {
-    "id": "ai.librechat.cloudronapp",
+  "id": "ai.librechat.cloudronapp",
-    "version": "1.4.8",
+  "version": "1.4.5",
-    "title": "LibreChat",
+  "title": "LibreChat",
-    "upstreamVersion": "0.8.8",
+  "upstreamVersion": "0.8.8",
-    "author": "Danny Avila",
+  "author": "Danny Avila",
-    "description": "LibreChat is an open-source chatbot client that supports multiple AI providers and models including:\n\n- OpenAI GPT Models\n- Anthropic Claude Models\n- Google PaLM Models\n- Various open-source local models\n\nFeatures:\n- Switch between various AI models\n- Conversation history\n- Plugins support\n- File upload and processing\n- Custom instructions\n- Multiple conversation modes\n\n",
+  "description": "LibreChat is an open-source chatbot client that supports multiple AI providers and models including:\n\n- OpenAI GPT Models\n- Anthropic Claude Models\n- Google PaLM Models\n- Various open-source local models\n\nFeatures:\n- Switch between various AI models\n- Conversation history\n- Plugins support\n- File upload and processing\n- Custom instructions\n- Multiple conversation modes\n\n",
-    "changelog": "* Update uv to 0.13.5\n",
+  "changelog": "* Update uv to 0.13.5\n",
-    "tagline": "ChatGPT-like interface with model switching",
+  "tagline": "ChatGPT-like interface with model switching",
-    "website": "https://github.com/danny-avila/LibreChat",
+  "website": "https://github.com/danny-avila/LibreChat",
-    "documentationUrl": "https://docs.cloudron.io/packages/librechat/",
+  "documentationUrl": "https://docs.cloudron.io/packages/librechat/",
-    "forumUrl": "https://forum.cloudron.io/category/210/librechat",
+  "forumUrl": "https://forum.cloudron.io/category/210/librechat",
-    "contactEmail": "support@cloudron.io",
+  "contactEmail": "support@cloudron.io",
-    "healthCheckPath": "/health",
+  "healthCheckPath": "/health",
-    "httpPort": 3080,
+  "httpPort": 3080,
-    "addons": {
+  "addons": {
-        "postgresql": {},
+    "postgresql": {},
-        "mongodb": {},
+    "mongodb": {},
-        "localstorage": {},
+    "localstorage": {},
-        "oidc": {
+    "oidc": {
-            "loginRedirectUri": "/oauth/openid/callback"
+      "loginRedirectUri": "/oauth/openid/callback"
-        },
-        "sendmail": {
-            "supportsDisplayName": true
-        },
-        "scheduler": {
-            "librechat_key_sync": {
-                "schedule": "* * * * *",
-                "command": "cd /app/code/librechat/api && node /app/code/sync-keys.js"
-            }
-        }
     },
-    "checklist": {
+    "sendmail": {
-        "register-admin": {
+      "supportsDisplayName": true
-            "message": "On the first visit, register yourself as an admin user"
-        },
-        "disable-registration": {
-            "message": "Disable registration, if required, to prevent misuse"
-        },
-        "set-api-keys": {
-            "message": "Set API keys in /app/data/env file and restart the app"
-        }
     },
-    "optionalSso": true,
+    "scheduler": {
-    "manifestVersion": 2,
+      "librechat_key_sync": {
-    "memoryLimit": 1073741824,
+        "schedule": "* * * * *",
-    "minBoxVersion": "8.1.0",
+        "command": "cd /app/code/librechat/api && node /app/code/sync-keys.js"
-    "tags": [
+      }
-        "ai",
+    }
-        "chat",
+  },
-        "gpt"
+  "checklist": {
-    ],
+    "register-admin": {
-    "mediaLinks": [
+      "message": "On the first visit, register yourself as an admin user"
-        "https://screenshots.cloudron.io/ai.librechat.cloudronapp/librechat-00.png",
+    },
-        "https://screenshots.cloudron.io/ai.librechat.cloudronapp/librechat-01.png"
+    "disable-registration": {
-    ],
+      "message": "Disable registration, if required, to prevent misuse"
-    "icon": "file://logo.png",
+    },
-    "dockerImage": "registry.inference.coop/co-op/librechat-custom:20261106-c2aec74"
+    "set-api-keys": {
+      "message": "Set API keys in /app/data/env file and restart the app"
+    }
+  },
+  "optionalSso": true,
+  "manifestVersion": 2,
+  "memoryLimit": 1073741824,
+  "minBoxVersion": "8.1.0",
+  "tags": [
+    "ai",
+    "chat",
+    "gpt"
+  ],
+  "mediaLinks": [
+    "https://screenshots.cloudron.io/ai.librechat.cloudronapp/librechat-00.png",
+    "https://screenshots.cloudron.io/ai.librechat.cloudronapp/librechat-01.png"
+  ],
+  "icon": "file://logo.png",
+  "dockerImage": "registry.inference.coop/co-op/librechat-custom:20261031-2a98892"
 }

Dockerfile

@@ -20,7 +20,7 @@
 #      the manifest's scheduler task). All other behavior lives on the
 #      persistent volume (/app/data/librechat.yaml, /app/data/env,
 #      /app/data/mcp/) and survives image updates unchanged.
-FROM cloudron/ai.librechat.cloudronapp:202611030321030000
+FROM cloudron/ai.librechat.cloudronapp:202610230221180000
 
 # Login-page + header logo (the client bundle references assets/logo.svg)
 COPY assets/logo.svg /app/code/librechat/client/dist/assets/logo.svg

librechat.yaml

@@ -166,12 +166,6 @@ speech:
     advancedMode: false
     speechToText:
       engineSTT: external
-      # Pin the transcription LANGUAGE default to English. Without it the
-      # client sends no language param and voxtral-small-24b auto-detects —
-      # which misfired once as Spanish on a short first mic press (reported
-      # 2026-11-07). Members who save their own language in Settings -> Speech
-      # always override this default.
-      languageSTT: "en"
     textToSpeech:
       engineTTS: external
       voice: casual_female

release.sh

@@ -28,7 +28,7 @@ set -euo pipefail
 APP=${APP:-4023ccbf-d57a-4500-97df-14de9cf3516e}
 REGISTRY_REPO=${REGISTRY_REPO:-registry.inference.coop/co-op/librechat-custom}
 SERVER=${SERVER:-my.inference.coop}
-BASE_IMAGE=${BASE_IMAGE:-cloudron/ai.librechat.cloudronapp:202611030321030000}
+BASE_IMAGE=${BASE_IMAGE:-cloudron/ai.librechat.cloudronapp:202610150224320000}
 MANIFEST=CloudronManifest.json
 
 die() { printf 'release.sh: %s\n' "$*" >&2; exit 1; }