iobroker.assistant 1.4.5 → 1.4.6

package/README.md

@@ -235,6 +235,9 @@ train it twice.
     Placeholder for the next version (at the beginning of the line):
     ### **WORK IN PROGRESS**
 -->
+### 1.4.6 (2026-11-03)
+* (@GermanBluefox) Speech recognition: own OpenAI-compatible server (Voice tab, provider OpenAI, "Speech recognition server"), e.g. a local whisper-large-v3-turbo in speaches, faster-whisper-server or LocalAI. It needs no OpenAI key and never gets it; an own key for the server is optional
+
 ### 1.4.5 (2026-11-03)
 * (@GermanBluefox) ESPHome satellites: spoken replies go out in the format the device's media player announces (FLAC at its sample rate, as Home Assistant does; MP3/Opus via ffmpeg). Since ESPHome 2026.10 the player is built with only the codecs its pipelines use, and a WAV reply did not play at all. Devices that announce no formats keep getting WAV
 * (@GermanBluefox) ESPHome satellites: when the device ends the conversation itself (button, or the wake word said again), it now gets its RUN_END. It stayed in the conversation, and every further wake word only sent another stop

package/admin/i18n/de.json

@@ -58,7 +58,7 @@
   "ESPHome satellites": "ESPHome-Satelliten",
   "ESPHome satellites do not get the reply over their API socket — they fetch it as a URL. This is the port that small HTTP server listens on.": "ESPHome-Satelliten bekommen die Antwort nicht über ihren API-Socket — sie holen sie als URL ab. Das ist der Port, auf dem dieser kleine HTTP-Server lauscht.",
   "Empty = tts-1. Also: tts-1-hd, gpt-4o-mini-tts.": "Leer = tts-1. Auch: tts-1-hd, gpt-4o-mini-tts.",
-  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe.": "Leer = whisper-1. Auch: gpt-4o-transcribe, gpt-4o-mini-transcribe.",
+  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe. With an own server: the model as that server names it, e.g. Systran/faster-whisper-large-v3-turbo.": "Leer = whisper-1. Auch: gpt-4o-transcribe, gpt-4o-mini-transcribe. Mit eigenem Server: das Modell so, wie der Server es nennt, z. B. Systran/faster-whisper-large-v3-turbo.",
   "Enable voice (STT/TTS for satellites)": "Sprache aktivieren (STT/TTS für Satelliten)",
   "Enable voice server (satellites)": "Sprach-Server aktivieren (Satelliten)",
   "Enables speech recognition/synthesis. ioBroker-native satellites reach it over the message bus — no port needed. Turn on the UDP server below only for ESP / Hannah satellites.": "Aktiviert Spracherkennung/-synthese. ioBroker-native Satelliten erreichen sie über den Nachrichtenbus — kein Port nötig. Den UDP-Server unten nur für ESP-/Hannah-Satelliten einschalten.",
@@ -222,5 +222,9 @@
   "Person": "Person",
   "Guest": "Gast",
   "Pet": "Haustier",
-  "Group": "Gruppe"
+  "Group": "Gruppe",
+  "Speech recognition server (optional)": "Server für die Spracherkennung (optional)",
+  "OpenAI-compatible server instead of OpenAI, e.g. a local Whisper: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Empty = OpenAI.": "OpenAI-kompatibler Server statt OpenAI, z. B. ein lokales Whisper: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Leer = OpenAI.",
+  "Key of the speech recognition server": "Schlüssel des Spracherkennungs-Servers",
+  "Only if the server wants one. The OpenAI key is never sent to it.": "Nur, wenn der Server einen verlangt. Der OpenAI-Schlüssel wird nie dorthin geschickt."
 }

package/admin/i18n/en.json

@@ -58,7 +58,7 @@
   "ESPHome satellites": "ESPHome satellites",
   "ESPHome satellites do not get the reply over their API socket — they fetch it as a URL. This is the port that small HTTP server listens on.": "ESPHome satellites do not get the reply over their API socket — they fetch it as a URL. This is the port that small HTTP server listens on.",
   "Empty = tts-1. Also: tts-1-hd, gpt-4o-mini-tts.": "Empty = tts-1. Also: tts-1-hd, gpt-4o-mini-tts.",
-  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe.": "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe.",
+  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe. With an own server: the model as that server names it, e.g. Systran/faster-whisper-large-v3-turbo.": "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe. With an own server: the model as that server names it, e.g. Systran/faster-whisper-large-v3-turbo.",
   "Enable voice (STT/TTS for satellites)": "Enable voice (STT/TTS for satellites)",
   "Enable voice server (satellites)": "Enable voice server (satellites)",
   "Enables speech recognition/synthesis. ioBroker-native satellites reach it over the message bus — no port needed. Turn on the UDP server below only for ESP / Hannah satellites.": "Enables speech recognition/synthesis. ioBroker-native satellites reach it over the message bus — no port needed. Turn on the UDP server below only for ESP / Hannah satellites.",
@@ -222,5 +222,9 @@
   "Person": "Person",
   "Guest": "Guest",
   "Pet": "Pet",
-  "Group": "Group"
+  "Group": "Group",
+  "Speech recognition server (optional)": "Speech recognition server (optional)",
+  "OpenAI-compatible server instead of OpenAI, e.g. a local Whisper: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Empty = OpenAI.": "OpenAI-compatible server instead of OpenAI, e.g. a local Whisper: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Empty = OpenAI.",
+  "Key of the speech recognition server": "Key of the speech recognition server",
+  "Only if the server wants one. The OpenAI key is never sent to it.": "Only if the server wants one. The OpenAI key is never sent to it."
 }

package/admin/i18n/es.json

@@ -58,7 +58,7 @@
   "ESPHome satellites": "Satélites ESPHome",
   "ESPHome satellites do not get the reply over their API socket — they fetch it as a URL. This is the port that small HTTP server listens on.": "Los satélites ESPHome no reciben la respuesta por su socket de API: la descargan como URL. Este es el puerto en el que escucha ese pequeño servidor HTTP.",
   "Empty = tts-1. Also: tts-1-hd, gpt-4o-mini-tts.": "Vacío = tts-1. También: tts-1-hd, gpt-4o-mini-tts.",
-  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe.": "Vacío = whisper-1. También: gpt-4o-transcribe, gpt-4o-mini-transcribe.",
+  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe. With an own server: the model as that server names it, e.g. Systran/faster-whisper-large-v3-turbo.": "Vacío = whisper-1. También: gpt-4o-transcribe, gpt-4o-mini-transcribe. Con un servidor propio: el modelo tal como lo llama el servidor, p. ej. Systran/faster-whisper-large-v3-turbo.",
   "Enable voice (STT/TTS for satellites)": "Habilitar la voz (STT/TTS para satélites)",
   "Enable voice server (satellites)": "Habilitar servidor de voz (satélites)",
   "Enables speech recognition/synthesis. ioBroker-native satellites reach it over the message bus — no port needed. Turn on the UDP server below only for ESP / Hannah satellites.": "Permite el reconocimiento/síntesis de voz. Los satélites nativos de ioBroker se conectan a través del bus de mensajes; no se necesita ningún puerto. Active el servidor UDP que se indica a continuación solo para los satélites ESP/Hannah.",
@@ -222,5 +222,9 @@
   "Person": "Persona",
   "Guest": "Invitado",
   "Pet": "Mascota",
-  "Group": "Grupo"
+  "Group": "Grupo",
+  "Speech recognition server (optional)": "Servidor de reconocimiento de voz (opcional)",
+  "OpenAI-compatible server instead of OpenAI, e.g. a local Whisper: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Empty = OpenAI.": "Servidor compatible con OpenAI en lugar de OpenAI, p. ej. un Whisper local: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Vacío = OpenAI.",
+  "Key of the speech recognition server": "Clave del servidor de reconocimiento de voz",
+  "Only if the server wants one. The OpenAI key is never sent to it.": "Solo si el servidor la pide. La clave de OpenAI nunca se envía allí."
 }

package/admin/i18n/fr.json

@@ -58,7 +58,7 @@
   "ESPHome satellites": "Satellites ESPHome",
   "ESPHome satellites do not get the reply over their API socket — they fetch it as a URL. This is the port that small HTTP server listens on.": "Les satellites ESPHome ne reçoivent pas la réponse par leur socket API : ils la récupèrent via une URL. C’est le port sur lequel écoute ce petit serveur HTTP.",
   "Empty = tts-1. Also: tts-1-hd, gpt-4o-mini-tts.": "Vide = tts-1. Également : tts-1-hd, gpt-4o-mini-tts.",
-  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe.": "Vide = whisper-1. Également : gpt-4o-transcribe, gpt-4o-mini-transcribe.",
+  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe. With an own server: the model as that server names it, e.g. Systran/faster-whisper-large-v3-turbo.": "Vide = whisper-1. Également : gpt-4o-transcribe, gpt-4o-mini-transcribe. Avec un serveur propre : le modèle tel que le serveur le nomme, p. ex. Systran/faster-whisper-large-v3-turbo.",
   "Enable voice (STT/TTS for satellites)": "Activer la voix (STT/TTS pour les satellites)",
   "Enable voice server (satellites)": "Activer le serveur vocal (satellites)",
   "Enables speech recognition/synthesis. ioBroker-native satellites reach it over the message bus — no port needed. Turn on the UDP server below only for ESP / Hannah satellites.": "Permet la reconnaissance et la synthèse vocales. Les satellites natifs d'ioBroker y accèdent via le bus de messages ; aucun port n'est nécessaire. Activez le serveur UDP ci-dessous uniquement pour les satellites ESP/Hannah.",
@@ -222,5 +222,9 @@
   "Person": "Personne",
   "Guest": "Invité",
   "Pet": "Animal",
-  "Group": "Groupe"
+  "Group": "Groupe",
+  "Speech recognition server (optional)": "Serveur de reconnaissance vocale (facultatif)",
+  "OpenAI-compatible server instead of OpenAI, e.g. a local Whisper: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Empty = OpenAI.": "Serveur compatible OpenAI à la place d'OpenAI, p. ex. un Whisper local : http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Vide = OpenAI.",
+  "Key of the speech recognition server": "Clé du serveur de reconnaissance vocale",
+  "Only if the server wants one. The OpenAI key is never sent to it.": "Seulement si le serveur en demande une. La clé OpenAI n'y est jamais envoyée."
 }

package/admin/i18n/it.json

@@ -58,7 +58,7 @@
   "ESPHome satellites": "Satelliti ESPHome",
   "ESPHome satellites do not get the reply over their API socket — they fetch it as a URL. This is the port that small HTTP server listens on.": "I satelliti ESPHome non ricevono la risposta dal loro socket API: la scaricano come URL. Questa è la porta su cui ascolta quel piccolo server HTTP.",
   "Empty = tts-1. Also: tts-1-hd, gpt-4o-mini-tts.": "Vuoto = tts-1. Anche: tts-1-hd, gpt-4o-mini-tts.",
-  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe.": "Vuoto = whisper-1. Anche: gpt-4o-transcribe, gpt-4o-mini-transcribe.",
+  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe. With an own server: the model as that server names it, e.g. Systran/faster-whisper-large-v3-turbo.": "Vuoto = whisper-1. Anche: gpt-4o-transcribe, gpt-4o-mini-transcribe. Con un server proprio: il modello come lo chiama il server, ad es. Systran/faster-whisper-large-v3-turbo.",
   "Enable voice (STT/TTS for satellites)": "Abilita la voce (STT/TTS per i satelliti)",
   "Enable voice server (satellites)": "Abilita il server vocale (satelliti)",
   "Enables speech recognition/synthesis. ioBroker-native satellites reach it over the message bus — no port needed. Turn on the UDP server below only for ESP / Hannah satellites.": "Abilita il riconoscimento/sintesi vocale. I satelliti nativi di ioBroker lo raggiungono tramite il bus di messaggi, senza bisogno di porte. Attivare il server UDP qui sotto solo per i satelliti ESP/Hannah.",
@@ -222,5 +222,9 @@
   "Person": "Persona",
   "Guest": "Ospite",
   "Pet": "Animale",
-  "Group": "Gruppo"
+  "Group": "Gruppo",
+  "Speech recognition server (optional)": "Server di riconoscimento vocale (facoltativo)",
+  "OpenAI-compatible server instead of OpenAI, e.g. a local Whisper: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Empty = OpenAI.": "Server compatibile con OpenAI al posto di OpenAI, ad es. un Whisper locale: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Vuoto = OpenAI.",
+  "Key of the speech recognition server": "Chiave del server di riconoscimento vocale",
+  "Only if the server wants one. The OpenAI key is never sent to it.": "Solo se il server ne richiede una. La chiave OpenAI non viene mai inviata lì."
 }

package/admin/i18n/nl.json

@@ -58,7 +58,7 @@
   "ESPHome satellites": "ESPHome-satellieten",
   "ESPHome satellites do not get the reply over their API socket — they fetch it as a URL. This is the port that small HTTP server listens on.": "ESPHome-satellieten krijgen het antwoord niet via hun API-socket — ze halen het op als URL. Dit is de poort waarop die kleine HTTP-server luistert.",
   "Empty = tts-1. Also: tts-1-hd, gpt-4o-mini-tts.": "Leeg = tts-1. Ook: tts-1-hd, gpt-4o-mini-tts.",
-  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe.": "Leeg = whisper-1. Ook: gpt-4o-transcribe, gpt-4o-mini-transcribe.",
+  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe. With an own server: the model as that server names it, e.g. Systran/faster-whisper-large-v3-turbo.": "Leeg = whisper-1. Ook: gpt-4o-transcribe, gpt-4o-mini-transcribe. Met een eigen server: het model zoals de server het noemt, bijv. Systran/faster-whisper-large-v3-turbo.",
   "Enable voice (STT/TTS for satellites)": "Schakel spraak in (STT/TTS voor satellieten)",
   "Enable voice server (satellites)": "Schakel de spraakserver (satellieten) in.",
   "Enables speech recognition/synthesis. ioBroker-native satellites reach it over the message bus — no port needed. Turn on the UDP server below only for ESP / Hannah satellites.": "Maakt spraakherkenning/synthese mogelijk. ioBroker-native satellieten bereiken deze via de berichtenbus — er is geen poort nodig. Schakel de onderstaande UDP-server alleen in voor ESP/Hannah-satellieten.",
@@ -222,5 +222,9 @@
   "Person": "Persoon",
   "Guest": "Gast",
   "Pet": "Huisdier",
-  "Group": "Groep"
+  "Group": "Groep",
+  "Speech recognition server (optional)": "Server voor spraakherkenning (optioneel)",
+  "OpenAI-compatible server instead of OpenAI, e.g. a local Whisper: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Empty = OpenAI.": "OpenAI-compatibele server in plaats van OpenAI, bijv. een lokale Whisper: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Leeg = OpenAI.",
+  "Key of the speech recognition server": "Sleutel van de spraakherkenningsserver",
+  "Only if the server wants one. The OpenAI key is never sent to it.": "Alleen als de server er een vraagt. De OpenAI-sleutel wordt er nooit naartoe gestuurd."
 }

package/admin/i18n/pl.json

@@ -58,7 +58,7 @@
   "ESPHome satellites": "Satelity ESPHome",
   "ESPHome satellites do not get the reply over their API socket — they fetch it as a URL. This is the port that small HTTP server listens on.": "Satelity ESPHome nie odbierają odpowiedzi przez swoje gniazdo API — pobierają ją jako URL. To port, na którym nasłuchuje ten mały serwer HTTP.",
   "Empty = tts-1. Also: tts-1-hd, gpt-4o-mini-tts.": "Pusty = tts-1. Również: tts-1-hd, gpt-4o-mini-tts.",
-  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe.": "Pusty = szept-1. Również: gpt-4o-transcribe, gpt-4o-mini-transcribe.",
+  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe. With an own server: the model as that server names it, e.g. Systran/faster-whisper-large-v3-turbo.": "Puste = whisper-1. Również: gpt-4o-transcribe, gpt-4o-mini-transcribe. Z własnym serwerem: model tak, jak nazywa go serwer, np. Systran/faster-whisper-large-v3-turbo.",
   "Enable voice (STT/TTS for satellites)": "Włącz głos (STT/TTS dla satelitów)",
   "Enable voice server (satellites)": "Włącz serwer głosowy (satelity)",
   "Enables speech recognition/synthesis. ioBroker-native satellites reach it over the message bus — no port needed. Turn on the UDP server below only for ESP / Hannah satellites.": "Umożliwia rozpoznawanie/syntezę mowy. Satelity natywne dla ioBroker osiągają go przez magistralę komunikatów — nie jest potrzebny żaden port. Włącz serwer UDP poniżej tylko dla satelitów ESP/Hannah.",
@@ -222,5 +222,9 @@
   "Person": "Osoba",
   "Guest": "Gość",
   "Pet": "Zwierzę",
-  "Group": "Grupa"
+  "Group": "Grupa",
+  "Speech recognition server (optional)": "Serwer rozpoznawania mowy (opcjonalnie)",
+  "OpenAI-compatible server instead of OpenAI, e.g. a local Whisper: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Empty = OpenAI.": "Serwer zgodny z OpenAI zamiast OpenAI, np. lokalny Whisper: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Puste = OpenAI.",
+  "Key of the speech recognition server": "Klucz serwera rozpoznawania mowy",
+  "Only if the server wants one. The OpenAI key is never sent to it.": "Tylko jeśli serwer go wymaga. Klucz OpenAI nigdy nie jest tam wysyłany."
 }

package/admin/i18n/pt.json

@@ -58,7 +58,7 @@
   "ESPHome satellites": "Satélites ESPHome",
   "ESPHome satellites do not get the reply over their API socket — they fetch it as a URL. This is the port that small HTTP server listens on.": "Os satélites ESPHome não recebem a resposta pelo seu socket de API — buscam-na como URL. Esta é a porta em que esse pequeno servidor HTTP escuta.",
   "Empty = tts-1. Also: tts-1-hd, gpt-4o-mini-tts.": "Vazio = tts-1. Também: tts-1-hd, gpt-4o-mini-tts.",
-  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe.": "Vazio = whisper-1. Também: gpt-4o-transcribe, gpt-4o-mini-transcribe.",
+  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe. With an own server: the model as that server names it, e.g. Systran/faster-whisper-large-v3-turbo.": "Vazio = whisper-1. Também: gpt-4o-transcribe, gpt-4o-mini-transcribe. Com servidor próprio: o modelo como o servidor o chama, p. ex. Systran/faster-whisper-large-v3-turbo.",
   "Enable voice (STT/TTS for satellites)": "Ativar voz (STT/TTS para satélites)",
   "Enable voice server (satellites)": "Ativar servidor de voz (satélites)",
   "Enables speech recognition/synthesis. ioBroker-native satellites reach it over the message bus — no port needed. Turn on the UDP server below only for ESP / Hannah satellites.": "Habilita o reconhecimento/síntese de voz. Os satélites nativos do ioBroker acessam o servidor através do barramento de mensagens — sem necessidade de porta. Ative o servidor UDP abaixo apenas para satélites ESP/Hannah.",
@@ -222,5 +222,9 @@
   "Person": "Pessoa",
   "Guest": "Convidado",
   "Pet": "Animal de estimação",
-  "Group": "Grupo"
+  "Group": "Grupo",
+  "Speech recognition server (optional)": "Servidor de reconhecimento de voz (opcional)",
+  "OpenAI-compatible server instead of OpenAI, e.g. a local Whisper: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Empty = OpenAI.": "Servidor compatível com OpenAI em vez da OpenAI, p. ex. um Whisper local: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Vazio = OpenAI.",
+  "Key of the speech recognition server": "Chave do servidor de reconhecimento de voz",
+  "Only if the server wants one. The OpenAI key is never sent to it.": "Só se o servidor pedir uma. A chave da OpenAI nunca é enviada para lá."
 }

package/admin/i18n/ru.json

@@ -58,7 +58,7 @@
   "ESPHome satellites": "Сателлиты ESPHome",
   "ESPHome satellites do not get the reply over their API socket — they fetch it as a URL. This is the port that small HTTP server listens on.": "Сателлиты ESPHome получают ответ не через свой сокет API — они забирают его по URL. Это порт, на котором слушает этот небольшой HTTP-сервер.",
   "Empty = tts-1. Also: tts-1-hd, gpt-4o-mini-tts.": "Пусто = tts-1. Также: tts-1-hd, gpt-4o-mini-tts.",
-  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe.": "Пусто = whisper-1. Также: gpt-4o-transcribe, gpt-4o-mini-transcribe.",
+  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe. With an own server: the model as that server names it, e.g. Systran/faster-whisper-large-v3-turbo.": "Пусто = whisper-1. Также: gpt-4o-transcribe, gpt-4o-mini-transcribe. Со своим сервером: модель так, как её называет сервер, напр. Systran/faster-whisper-large-v3-turbo.",
   "Enable voice (STT/TTS for satellites)": "Включить голосовую связь (STT/TTS для спутниковой связи)",
   "Enable voice server (satellites)": "Включить голосовой сервер (спутники)",
   "Enables speech recognition/synthesis. ioBroker-native satellites reach it over the message bus — no port needed. Turn on the UDP server below only for ESP / Hannah satellites.": "Включает распознавание/синтез речи. Спутники, использующие ioBroker, получают к нему доступ через шину сообщений — порт не требуется. Включите UDP-сервер, указанный ниже, только для спутников ESP/Hannah.",
@@ -222,5 +222,9 @@
   "Person": "Человек",
   "Guest": "Гость",
   "Pet": "Питомец",
-  "Group": "Группа"
+  "Group": "Группа",
+  "Speech recognition server (optional)": "Сервер распознавания речи (опционально)",
+  "OpenAI-compatible server instead of OpenAI, e.g. a local Whisper: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Empty = OpenAI.": "OpenAI-совместимый сервер вместо OpenAI, напр. локальный Whisper: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Пусто = OpenAI.",
+  "Key of the speech recognition server": "Ключ сервера распознавания речи",
+  "Only if the server wants one. The OpenAI key is never sent to it.": "Только если сервер его требует. Ключ OpenAI туда никогда не отправляется."
 }

package/admin/i18n/uk.json

@@ -58,7 +58,7 @@
   "ESPHome satellites": "Сателіти ESPHome",
   "ESPHome satellites do not get the reply over their API socket — they fetch it as a URL. This is the port that small HTTP server listens on.": "Сателіти ESPHome отримують відповідь не через свій сокет API — вони забирають її за URL. Це порт, на якому слухає цей невеликий HTTP-сервер.",
   "Empty = tts-1. Also: tts-1-hd, gpt-4o-mini-tts.": "Порожнє = tts-1. Також: tts-1-hd, gpt-4o-mini-tts.",
-  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe.": "Порожнє = шепіт-1. Також: gpt-4o-trancribe, gpt-4o-mini-trancribe.",
+  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe. With an own server: the model as that server names it, e.g. Systran/faster-whisper-large-v3-turbo.": "Порожньо = whisper-1. Також: gpt-4o-transcribe, gpt-4o-mini-transcribe. З власним сервером: модель так, як її називає сервер, напр. Systran/faster-whisper-large-v3-turbo.",
   "Enable voice (STT/TTS for satellites)": "Увімкнути голосовий зв'язок (STT/TTS для супутників)",
   "Enable voice server (satellites)": "Увімкнути голосовий сервер (супутники)",
   "Enables speech recognition/synthesis. ioBroker-native satellites reach it over the message bus — no port needed. Turn on the UDP server below only for ESP / Hannah satellites.": "Дозволяє розпізнавання/синтез мовлення. Супутники, сумісні з ioBroker, досягають його через шину повідомлень — порт не потрібен. Увімкніть UDP-сервер нижче лише для супутників ESP / Hannah.",
@@ -222,5 +222,9 @@
   "Person": "Людина",
   "Guest": "Гість",
   "Pet": "Улюбленець",
-  "Group": "Група"
+  "Group": "Група",
+  "Speech recognition server (optional)": "Сервер розпізнавання мовлення (необов'язково)",
+  "OpenAI-compatible server instead of OpenAI, e.g. a local Whisper: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Empty = OpenAI.": "OpenAI-сумісний сервер замість OpenAI, напр. локальний Whisper: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Порожньо = OpenAI.",
+  "Key of the speech recognition server": "Ключ сервера розпізнавання мовлення",
+  "Only if the server wants one. The OpenAI key is never sent to it.": "Лише якщо сервер його вимагає. Ключ OpenAI туди ніколи не надсилається."
 }

package/admin/i18n/zh-cn.json

@@ -58,7 +58,7 @@
   "ESPHome satellites": "ESPHome 卫星",
   "ESPHome satellites do not get the reply over their API socket — they fetch it as a URL. This is the port that small HTTP server listens on.": "ESPHome 卫星不会通过其 API 套接字接收回复，而是按 URL 获取。这里就是那个小型 HTTP 服务器监听的端口。",
   "Empty = tts-1. Also: tts-1-hd, gpt-4o-mini-tts.": "空 = tts-1。另见：tts-1-hd、gpt-4o-mini-tts。",
-  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe.": "空 = whisper-1。另见：gpt-4o-transcribe、gpt-4o-mini-transcribe。",
+  "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe. With an own server: the model as that server names it, e.g. Systran/faster-whisper-large-v3-turbo.": "空 = whisper-1。另见：gpt-4o-transcribe、gpt-4o-mini-transcribe。使用自己的服务器时：按服务器的名称填写模型，例如 Systran/faster-whisper-large-v3-turbo。",
   "Enable voice (STT/TTS for satellites)": "启用语音功能（卫星语音转语音/文本转语音）",
   "Enable voice server (satellites)": "启用语音服务器（卫星）",
   "Enables speech recognition/synthesis. ioBroker-native satellites reach it over the message bus — no port needed. Turn on the UDP server below only for ESP / Hannah satellites.": "启用语音识别/合成功能。ioBroker 原生卫星通过消息总线与其通信，无需端口。仅当 ESP/Hannah 卫星连接时，才需要启用下方的 UDP 服务器。",
@@ -222,5 +222,9 @@
   "Person": "人员",
   "Guest": "访客",
   "Pet": "宠物",
-  "Group": "组"
+  "Group": "组",
+  "Speech recognition server (optional)": "语音识别服务器（可选）",
+  "OpenAI-compatible server instead of OpenAI, e.g. a local Whisper: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Empty = OpenAI.": "代替 OpenAI 的 OpenAI 兼容服务器，例如本地 Whisper：http://192.168.1.10:8000/v1（speaches、faster-whisper-server、LocalAI）。空 = OpenAI。",
+  "Key of the speech recognition server": "语音识别服务器的密钥",
+  "Only if the server wants one. The OpenAI key is never sent to it.": "仅当服务器需要时填写。OpenAI 密钥永远不会发送到该服务器。"
 }

package/admin/jsonConfig.json

@@ -1184,8 +1184,30 @@
                     "newLine": true,
                     "type": "text",
                     "label": "OpenAI STT model (optional)",
-                    "help": "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe.",
-                    "hidden": "!data.voiceEnabled || data.sttProvider !== 'openai'",
+                    "help": "Empty = whisper-1. Also: gpt-4o-transcribe, gpt-4o-mini-transcribe. With an own server: the model as that server names it, e.g. Systran/faster-whisper-large-v3-turbo.",
+                    "hidden": "!data.voiceEnabled || (data.sttProvider !== 'openai' && data.sttFallback !== 'openai')",
+                    "xs": 12,
+                    "sm": 6,
+                    "md": 4,
+                    "lg": 4,
+                    "xl": 4
+                },
+                "sttBaseUrl": {
+                    "type": "text",
+                    "label": "Speech recognition server (optional)",
+                    "help": "OpenAI-compatible server instead of OpenAI, e.g. a local Whisper: http://192.168.1.10:8000/v1 (speaches, faster-whisper-server, LocalAI). Empty = OpenAI.",
+                    "hidden": "!data.voiceEnabled || (data.sttProvider !== 'openai' && data.sttFallback !== 'openai')",
+                    "xs": 12,
+                    "sm": 6,
+                    "md": 4,
+                    "lg": 4,
+                    "xl": 4
+                },
+                "sttServerKey": {
+                    "type": "password",
+                    "label": "Key of the speech recognition server",
+                    "help": "Only if the server wants one. The OpenAI key is never sent to it.",
+                    "hidden": "!data.voiceEnabled || (data.sttProvider !== 'openai' && data.sttFallback !== 'openai') || !data.sttBaseUrl",
                     "xs": 12,
                     "sm": 6,
                     "md": 4,

package/build/lib/voice/engines.js

@@ -104,6 +104,9 @@ function buildSttEngine(provider, ctx) {
         case 'piper':
             throw new Error('Piper is a text-to-speech engine, not speech-to-text');
         default:
+            if (ctx.sttBaseUrl?.trim()) {
+                return new stt_1.OpenAiStt(ctx.sttServerKey || '', ctx.sttModel || undefined, ctx.sttBaseUrl);
+            }
             requireOpenAi(ctx.creds);
             return new stt_1.OpenAiStt(ctx.creds.openaiKey, ctx.sttModel || undefined);
     }

package/build/lib/voice/engines.js.map

@@ -1 +1 @@
-{"version":3,"file":"engines.js","sourceRoot":"","sources":["../../../src/lib/voice/engines.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AA+FA,0CAYC;AAuBD,0CAeC;AAuDD,gCAmBC;AAGD,sCAKC;AAGD,sCAEC;AAxOD;;;;GAIG;AACH,+BAAkD;AAClD,+BAAoE;AACpE,mCAA8D;AAC9D,+BAAuE;AACvE,iCAAiD;AACjD,mCAAoD;AACpD,6CAOsB;AACtB,gDAAkC;AAElC,yCAAuC;AACvC,yCAAwE;AACxE,iCAAqC;AAgDrC,SAAS,YAAY,CAAC,KAAuB;IACzC,IAAI,CAAC,KAAK,CAAC,QAAQ,IAAI,CAAC,KAAK,CAAC,WAAW,EAAE,CAAC;QACxC,MAAM,IAAI,KAAK,CAAC,kDAAkD,CAAC,CAAC;IACxE,CAAC;AACL,CAAC;AAED,SAAS,UAAU,CAAC,KAAuB;IACvC,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,WAAW,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,eAAe,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,MAAM,EAAE,CAAC;QAC5E,MAAM,IAAI,KAAK,CAAC,iEAAiE,CAAC,CAAC;IACvF,CAAC;AACL,CAAC;AAED,SAAS,aAAa,CAAC,KAAuB;IAC1C,IAAI,CAAC,KAAK,CAAC,SAAS,EAAE,CAAC;QACnB,MAAM,IAAI,KAAK,CAAC,gCAAgC,CAAC,CAAC;IACtD,CAAC;AACL,CAAC;AAED,SAAS,iBAAiB,CAAC,KAAuB;IAC9C,IAAI,CAAC,KAAK,CAAC,aAAa,EAAE,CAAC;QACvB,MAAM,IAAI,KAAK,CAAC,oCAAoC,CAAC,CAAC;IAC1D,CAAC;AACL,CAAC;AAED,SAAgB,eAAe,CAAC,QAAwB,EAAE,GAAkB;IACxE,MAAM,OAAO,GAA2B,EAAE,IAAI,EAAE,QAAQ,EAAE,MAAM,EAAE,cAAc,CAAC,QAAQ,EAAE,GAAG,CAAC,EAAE,CAAC;IAClG,MAAM,QAAQ,GAAG,GAAG,CAAC,WAAW,IAAI,GAAG,CAAC,WAAW,KAAK,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,WAAW,CAAC,CAAC,CAAC,EAAE,CAAC;IACxF,IAAI,CAAC,QAAQ,EAAE,CAAC;QACZ,OAAO,OAAO,CAAC,MAAM,CAAC;IAC1B,CAAC;IACD,IAAI,CAAC;QACD,OAAO,IAAI,sBAAW,CAAC,CAAC,OAAO,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,MAAM,EAAE,cAAc,CAAC,QAAQ,EAAE,GAAG,CAAC,EAAE,CAAC,EAAE,GAAG,CAAC,GAAG,CAAC,CAAC;IAC1G,CAAC;IAAC,OAAO,CAAC,EAAE,CAAC;QACT,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC,4BAA4B,QAAQ,kBAAmB,CAAW,CAAC,OAAO,EAAE,CAAC,CAAC;QAC3F,OAAO,OAAO,CAAC,MAAM,CAAC;IAC1B,CAAC;AACL,CAAC;AAED,SAAS,cAAc,CAAC,QAAwB,EAAE,GAAkB;IAChE,QAAQ,QAAQ,EAAE,CAAC;QACf,KAAK,OAAO;YACR,YAAY,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACxB,OAAO,IAAI,gBAAQ,CAAC,GAAG,CAAC,KAAK,CAAC,QAAQ,EAAE,GAAG,CAAC,KAAK,CAAC,WAAW,CAAC,CAAC;QACnE,KAAK,KAAK;YACN,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACtB,OAAO,IAAI,YAAM,CAAC,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC;QACrC,KAAK,MAAM;YACP,OAAO,IAAI,cAAO,CAAC,GAAG,CAAC,OAAO,EAAE,GAAG,CAAC,SAAS,EAAE,GAAG,CAAC,GAAG,CAAC,CAAC;QAC5D,KAAK,YAAY;YACb,iBAAiB,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YAC7B,OAAO,IAAI,0BAAa,CAAC,GAAG,CAAC,KAAK,CAAC,aAAa,EAAE,GAAG,CAAC,kBAAkB,CAAC,CAAC;QAC9E,KAAK,OAAO;YACR,MAAM,IAAI,KAAK,CAAC,sDAAsD,CAAC,CAAC;QAC5E;YACI,aAAa,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACzB,OAAO,IAAI,eAAS,CAAC,GAAG,CAAC,KAAK,CAAC,SAAS,EAAE,GAAG,CAAC,QAAQ,IAAI,SAAS,CAAC,CAAC;IAC7E,CAAC;AACL,CAAC;AAED,SAAgB,eAAe,CAAC,QAAwB,EAAE,GAAkB;IACxE,sGAAsG;IACtG,iGAAiG;IACjG,MAAM,OAAO,GAA2B,EAAE,IAAI,EAAE,QAAQ,EAAE,MAAM,EAAE,SAAS,CAAC,QAAQ,EAAE,GAAG,CAAC,EAAE,CAAC;IAC7F,MAAM,QAAQ,GAAG,GAAG,CAAC,WAAW,IAAI,GAAG,CAAC,WAAW,KAAK,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,WAAW,CAAC,CAAC,CAAC,EAAE,CAAC;IACxF,IAAI,CAAC,QAAQ,EAAE,CAAC;QACZ,OAAO,OAAO,CAAC,MAAM,CAAC;IAC1B,CAAC;IACD,IAAI,CAAC;QACD,OAAO,IAAI,sBAAW,CAAC,CAAC,OAAO,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,MAAM,EAAE,SAAS,CAAC,QAAQ,EAAE,GAAG,CAAC,EAAE,CAAC,EAAE,GAAG,CAAC,GAAG,CAAC,CAAC;IACrG,CAAC;IAAC,OAAO,CAAC,EAAE,CAAC;QACT,sGAAsG;QACtG,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC,4BAA4B,QAAQ,kBAAmB,CAAW,CAAC,OAAO,EAAE,CAAC,CAAC;QAC3F,OAAO,OAAO,CAAC,MAAM,CAAC;IAC1B,CAAC;AACL,CAAC;AAED;;;GAGG;AACH,SAAS,SAAS,CAAC,QAAwB,EAAE,GAAkB;IAC3D,MAAM,KAAK,GACP,QAAQ,KAAK,OAAO;QAChB,CAAC,CAAC,GAAG,CAAC,MAAM,CAAC,KAAK;QAClB,CAAC,CAAC,QAAQ,KAAK,KAAK;YAClB,CAAC,CAAC,GAAG,CAAC,MAAM,CAAC,GAAG;YAChB,CAAC,CAAC,QAAQ,KAAK,OAAO;gBACpB,CAAC,CAAC,GAAG,CAAC,MAAM,CAAC,KAAK;gBAClB,CAAC,CAAC,QAAQ,KAAK,YAAY;oBACzB,CAAC,CAAC,GAAG,GAAG,CAAC,kBAAkB,IAAI,yCAA4B,IAAI,GAAG,CAAC,MAAM,CAAC,UAAU,EAAE;oBACtF,CAAC,CAAC,GAAG,CAAC,MAAM,CAAC,MAAM,CAAC;IAClC,MAAM,GAAG,GAAG,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,OAAO,EAAE,UAAU,EAAE,GAAG,QAAQ,IAAI,CAAC,KAAK,IAAI,SAAS,CAAC,CAAC,OAAO,CAAC,UAAU,EAAE,GAAG,CAAC,EAAE,CAAC,CAAC;IAC/G,OAAO,IAAI,oBAAS,CAAC,cAAc,CAAC,QAAQ,EAAE,GAAG,CAAC,EAAE,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,GAAG,EAAE,QAAQ,EAAE,GAAG,CAAC,WAAW,EAAE,CAAC,CAAC;AAC1G,CAAC;AAED,SAAS,cAAc,CAAC,QAAwB,EAAE,GAAkB;IAChE,QAAQ,QAAQ,EAAE,CAAC;QACf,KAAK,OAAO;YACR,YAAY,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACxB,OAAO,IAAI,gBAAQ,CAAC,GAAG,CAAC,KAAK,CAAC,QAAQ,EAAE,GAAG,CAAC,KAAK,CAAC,WAAW,EAAE,GAAG,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC;QACrF,KAAK,KAAK;YACN,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACtB,OAAO,IAAI,YAAM,CAAC,GAAG,CAAC,KAAK,CAAC,GAAG,EAAE,GAAG,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;QACrD,KAAK,OAAO;YACR,OAAO,IAAI,gBAAQ,CAAC,GAAG,CAAC,OAAO,EAAE,GAAG,CAAC,MAAM,CAAC,KAAK,EAAE,GAAG,CAAC,GAAG,CAAC,CAAC;QAChE,KAAK,MAAM;YACP,MAAM,IAAI,KAAK,CAAC,qDAAqD,CAAC,CAAC;QAC3E,KAAK,YAAY;YACb,iBAAiB,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YAC7B,OAAO,IAAI,0BAAa,CACpB,GAAG,CAAC,KAAK,CAAC,aAAa,EACvB,GAAG,CAAC,kBAAkB,EACtB,GAAG,CAAC,MAAM,CAAC,UAAU,EACrB,GAAG,CAAC,WAAW,CAClB,CAAC;QACN;YACI,aAAa,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACzB,OAAO,IAAI,eAAS,CAChB,GAAG,CAAC,KAAK,CAAC,SAAS,EACnB,CAAC,GAAG,CAAC,MAAM,CAAC,MAAM,IAAI,OAAO,CAAgB,EAC7C,GAAG,CAAC,QAAQ,IAAI,SAAS,CAC5B,CAAC;IACV,CAAC;AACL,CAAC;AAED,uDAAuD;AACvD,MAAM,aAAa,GAAG,CAAC,OAAO,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,MAAM,EAAE,SAAS,CAAC,CAAC;AAE5E,sFAAsF;AAC/E,KAAK,UAAU,UAAU,CAAC,QAAwB,EAAE,GAAkB,EAAE,QAAgB;IAC3F,QAAQ,QAAQ,EAAE,CAAC;QACf,KAAK,OAAO;YACR,YAAY,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACxB,OAAO,IAAA,uBAAe,EAAC,GAAG,CAAC,KAAK,CAAC,QAAQ,EAAE,GAAG,CAAC,KAAK,CAAC,WAAW,EAAE,IAAA,kBAAW,EAAC,QAAQ,CAAC,CAAC,CAAC;QAC7F,KAAK,KAAK;YACN,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACtB,OAAO,IAAA,qBAAe,EAAC,GAAG,CAAC,KAAK,CAAC,GAAG,EAAE,IAAA,kBAAW,EAAC,QAAQ,CAAC,CAAC,CAAC;QACjE,KAAK,OAAO;YACR,OAAO,IAAA,uBAAe,GAAE,CAAC;QAC7B,KAAK,YAAY,CAAC,CAAC,CAAC;YAChB,6DAA6D;YAC7D,MAAM,KAAK,GAAG,GAAG,CAAC,kBAAkB,IAAI,yCAA4B,CAAC;YACrE,MAAM,MAAM,GAAG,MAAM,IAAA,uCAA0B,EAAC,QAAQ,CAAC,CAAC;YAC1D,OAAO,IAAA,8BAAiB,EAAC,MAAM,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,KAAK,CAAC,EAAE,MAAM,IAAI,EAAE,EAAE,QAAQ,CAAC,CAAC;QACvF,CAAC;QACD;YACI,OAAO,aAAa,CAAC;IAC7B,CAAC;AACL,CAAC;AAED,kHAAkH;AAC3G,KAAK,UAAU,aAAa,CAAC,QAAwB,EAAE,QAAgB;IAC1E,IAAI,QAAQ,KAAK,YAAY,EAAE,CAAC;QAC5B,OAAO,CAAC,MAAM,IAAA,uCAA0B,EAAC,eAAe,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;IAC9E,CAAC;IACD,OAAO,QAAQ,KAAK,MAAM,CAAC,CAAC,CAAC,IAAA,qBAAc,EAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;AAC/D,CAAC;AAED,8FAA8F;AACvF,KAAK,UAAU,aAAa,CAAC,QAAwB;IACxD,OAAO,QAAQ,KAAK,YAAY,CAAC,CAAC,CAAC,CAAC,MAAM,IAAA,uCAA0B,EAAC,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;AACxG,CAAC","sourcesContent":["/**\n * Factory that builds the configured STT/TTS engine. Cloud engines (OpenAI/Azure/AWS) use resolved\n * credentials; local engines (Vosk/Piper) download their models on demand into the data dir.\n * Adding a provider = one new engine class + one `case` here.\n */\nimport { OpenAiStt, type SttEngine } from './stt';\nimport { OpenAiTts, type OpenAiVoice, type TtsEngine } from './tts';\nimport { AzureStt, AzureTts, listAzureVoices } from './azure';\nimport { AwsStt, AwsTts, listPollyVoices, type AwsCreds } from './aws';\nimport { VoskStt, listVoskModels } from './vosk';\nimport { PiperTts, listPiperVoices } from './piper';\nimport {\n    OpenRouterStt,\n    OpenRouterTts,\n    listOpenRouterSpeechModels,\n    voicesForLanguage,\n    DEFAULT_OPENROUTER_TTS_MODEL,\n    type AudioDecoder,\n} from './openrouter';\nimport * as path from 'node:path';\n\nimport { CachedTts } from './ttsCache';\nimport { FallbackStt, FallbackTts, type NamedEngine } from './fallback';\nimport { isoToLocale } from './lang';\nimport type { VoiceLogger } from './download';\n\nexport type SpeechProvider = 'openai' | 'openrouter' | 'azure' | 'aws' | 'vosk' | 'piper';\n\n/** All speech credentials, resolved from config (or the central credential store). */\nexport interface VoiceCredentials {\n    openaiKey: string;\n    openrouterKey: string;\n    azureKey: string;\n    azureRegion: string;\n    aws: AwsCreds;\n}\n\n/** Provider-specific voice ids (each provider names voices differently). */\nexport interface VoiceNames {\n    openai: string; // alloy/echo/…\n    azure: string; // e.g. de-DE-KatjaNeural\n    aws: string; // e.g. Vicki\n    piper: string; // e.g. de_DE-thorsten-medium\n    openrouter: string; // depends on the model, e.g. Kore, george\n}\n\n/** Everything the factory needs to build any engine. */\nexport interface EngineContext {\n    creds: VoiceCredentials;\n    voices: VoiceNames;\n    /** Optional second engine, used when the primary one fails ('' = none). */\n    sttFallback?: SpeechProvider | '';\n    ttsFallback?: SpeechProvider | '';\n    /** Writable instance data dir (for the local engines' downloads). */\n    dataDir: string;\n    log: VoiceLogger;\n    /** Local model overrides ('' → default per language). */\n    voskModel: string;\n    /** OpenAI STT model ('' → 'whisper-1'; e.g. 'gpt-4o-transcribe'). */\n    sttModel: string;\n    /** OpenAI TTS model ('' → 'tts-1'; e.g. 'gpt-4o-mini-tts'). */\n    ttsModel: string;\n    /** OpenRouter models ('' → the defaults of openrouter.ts) */\n    openrouterSttModel: string;\n    openrouterTtsModel: string;\n    /** Decoder for compressed speech (OpenRouter models that only return mp3); absent → those models fail */\n    decodeAudio?: AudioDecoder;\n    /** Longest text that is spoken, in characters; longer ones are cut at a sentence end. 0 = no limit, absent = 400. */\n    ttsMaxChars?: number;\n}\n\nfunction requireAzure(creds: VoiceCredentials): void {\n    if (!creds.azureKey || !creds.azureRegion) {\n        throw new Error('Azure speech needs a subscription key and region');\n    }\n}\n\nfunction requireAws(creds: VoiceCredentials): void {\n    if (!creds.aws.accessKeyId || !creds.aws.secretAccessKey || !creds.aws.region) {\n        throw new Error('AWS speech needs an access key id, secret access key and region');\n    }\n}\n\nfunction requireOpenAi(creds: VoiceCredentials): void {\n    if (!creds.openaiKey) {\n        throw new Error('OpenAI speech needs an API key');\n    }\n}\n\nfunction requireOpenRouter(creds: VoiceCredentials): void {\n    if (!creds.openrouterKey) {\n        throw new Error('OpenRouter speech needs an API key');\n    }\n}\n\nexport function createSttEngine(provider: SpeechProvider, ctx: EngineContext): SttEngine {\n    const primary: NamedEngine<SttEngine> = { name: provider, engine: buildSttEngine(provider, ctx) };\n    const fallback = ctx.sttFallback && ctx.sttFallback !== provider ? ctx.sttFallback : '';\n    if (!fallback) {\n        return primary.engine;\n    }\n    try {\n        return new FallbackStt([primary, { name: fallback, engine: buildSttEngine(fallback, ctx) }], ctx.log);\n    } catch (e) {\n        ctx.log.warn(`Speech-to-text fallback '${fallback}' unavailable: ${(e as Error).message}`);\n        return primary.engine;\n    }\n}\n\nfunction buildSttEngine(provider: SpeechProvider, ctx: EngineContext): SttEngine {\n    switch (provider) {\n        case 'azure':\n            requireAzure(ctx.creds);\n            return new AzureStt(ctx.creds.azureKey, ctx.creds.azureRegion);\n        case 'aws':\n            requireAws(ctx.creds);\n            return new AwsStt(ctx.creds.aws);\n        case 'vosk':\n            return new VoskStt(ctx.dataDir, ctx.voskModel, ctx.log);\n        case 'openrouter':\n            requireOpenRouter(ctx.creds);\n            return new OpenRouterStt(ctx.creds.openrouterKey, ctx.openrouterSttModel);\n        case 'piper':\n            throw new Error('Piper is a text-to-speech engine, not speech-to-text');\n        default:\n            requireOpenAi(ctx.creds);\n            return new OpenAiStt(ctx.creds.openaiKey, ctx.sttModel || undefined);\n    }\n}\n\nexport function createTtsEngine(provider: SpeechProvider, ctx: EngineContext): TtsEngine {\n    // Each engine gets the shared behaviour (disk cache, length limit, SSML) and its own cache directory,\n    // so a fallback engine's voice can never be served later while the primary one is healthy again.\n    const primary: NamedEngine<TtsEngine> = { name: provider, engine: cachedTts(provider, ctx) };\n    const fallback = ctx.ttsFallback && ctx.ttsFallback !== provider ? ctx.ttsFallback : '';\n    if (!fallback) {\n        return primary.engine;\n    }\n    try {\n        return new FallbackTts([primary, { name: fallback, engine: cachedTts(fallback, ctx) }], ctx.log);\n    } catch (e) {\n        // A fallback that cannot even be built (missing key, wrong provider) must not take the main one down.\n        ctx.log.warn(`Text-to-speech fallback '${fallback}' unavailable: ${(e as Error).message}`);\n        return primary.engine;\n    }\n}\n\n/**\n * One provider binding plus the shared cache/length/SSML layer. One cache directory per provider+voice —\n * a voice change must not serve audio in the old voice.\n */\nfunction cachedTts(provider: SpeechProvider, ctx: EngineContext): TtsEngine {\n    const voice =\n        provider === 'azure'\n            ? ctx.voices.azure\n            : provider === 'aws'\n              ? ctx.voices.aws\n              : provider === 'piper'\n                ? ctx.voices.piper\n                : provider === 'openrouter'\n                  ? `${ctx.openrouterTtsModel || DEFAULT_OPENROUTER_TTS_MODEL}-${ctx.voices.openrouter}`\n                  : ctx.voices.openai;\n    const dir = path.join(ctx.dataDir, 'ttscache', `${provider}-${(voice || 'default').replace(/[^\\w.-]/g, '_')}`);\n    return new CachedTts(buildTtsEngine(provider, ctx), { dir, log: ctx.log, maxChars: ctx.ttsMaxChars });\n}\n\nfunction buildTtsEngine(provider: SpeechProvider, ctx: EngineContext): TtsEngine {\n    switch (provider) {\n        case 'azure':\n            requireAzure(ctx.creds);\n            return new AzureTts(ctx.creds.azureKey, ctx.creds.azureRegion, ctx.voices.azure);\n        case 'aws':\n            requireAws(ctx.creds);\n            return new AwsTts(ctx.creds.aws, ctx.voices.aws);\n        case 'piper':\n            return new PiperTts(ctx.dataDir, ctx.voices.piper, ctx.log);\n        case 'vosk':\n            throw new Error('Vosk is a speech-to-text engine, not text-to-speech');\n        case 'openrouter':\n            requireOpenRouter(ctx.creds);\n            return new OpenRouterTts(\n                ctx.creds.openrouterKey,\n                ctx.openrouterTtsModel,\n                ctx.voices.openrouter,\n                ctx.decodeAudio,\n            );\n        default:\n            requireOpenAi(ctx.creds);\n            return new OpenAiTts(\n                ctx.creds.openaiKey,\n                (ctx.voices.openai || 'alloy') as OpenAiVoice,\n                ctx.ttsModel || undefined,\n            );\n    }\n}\n\n/** OpenAI TTS voices are a fixed set (no list API). */\nconst OPENAI_VOICES = ['alloy', 'echo', 'fable', 'onyx', 'nova', 'shimmer'];\n\n/** List the available TTS voices for a provider (for the settings voice dropdown). */\nexport async function listVoices(provider: SpeechProvider, ctx: EngineContext, language: string): Promise<string[]> {\n    switch (provider) {\n        case 'azure':\n            requireAzure(ctx.creds);\n            return listAzureVoices(ctx.creds.azureKey, ctx.creds.azureRegion, isoToLocale(language));\n        case 'aws':\n            requireAws(ctx.creds);\n            return listPollyVoices(ctx.creds.aws, isoToLocale(language));\n        case 'piper':\n            return listPiperVoices();\n        case 'openrouter': {\n            // public list, no key needed: the voices of the chosen model\n            const model = ctx.openrouterTtsModel || DEFAULT_OPENROUTER_TTS_MODEL;\n            const models = await listOpenRouterSpeechModels('speech');\n            return voicesForLanguage(models.find(m => m.id === model)?.voices || [], language);\n        }\n        default:\n            return OPENAI_VOICES;\n    }\n}\n\n/** Suggested STT model names for the settings dropdown: the local Vosk catalogue, or the models of OpenRouter. */\nexport async function listSttModels(provider: SpeechProvider, language: string): Promise<string[]> {\n    if (provider === 'openrouter') {\n        return (await listOpenRouterSpeechModels('transcription')).map(m => m.id);\n    }\n    return provider === 'vosk' ? listVoskModels(language) : [];\n}\n\n/** TTS model names for the settings dropdown — only OpenRouter has a choice worth listing. */\nexport async function listTtsModels(provider: SpeechProvider): Promise<string[]> {\n    return provider === 'openrouter' ? (await listOpenRouterSpeechModels('speech')).map(m => m.id) : [];\n}\n"]}
+{"version":3,"file":"engines.js","sourceRoot":"","sources":["../../../src/lib/voice/engines.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAsGA,0CAYC;AA0BD,0CAeC;AAuDD,gCAmBC;AAGD,sCAKC;AAGD,sCAEC;AAlPD;;;;GAIG;AACH,+BAAkD;AAClD,+BAAoE;AACpE,mCAA8D;AAC9D,+BAAuE;AACvE,iCAAiD;AACjD,mCAAoD;AACpD,6CAOsB;AACtB,gDAAkC;AAElC,yCAAuC;AACvC,yCAAwE;AACxE,iCAAqC;AAuDrC,SAAS,YAAY,CAAC,KAAuB;IACzC,IAAI,CAAC,KAAK,CAAC,QAAQ,IAAI,CAAC,KAAK,CAAC,WAAW,EAAE,CAAC;QACxC,MAAM,IAAI,KAAK,CAAC,kDAAkD,CAAC,CAAC;IACxE,CAAC;AACL,CAAC;AAED,SAAS,UAAU,CAAC,KAAuB;IACvC,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,WAAW,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,eAAe,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,MAAM,EAAE,CAAC;QAC5E,MAAM,IAAI,KAAK,CAAC,iEAAiE,CAAC,CAAC;IACvF,CAAC;AACL,CAAC;AAED,SAAS,aAAa,CAAC,KAAuB;IAC1C,IAAI,CAAC,KAAK,CAAC,SAAS,EAAE,CAAC;QACnB,MAAM,IAAI,KAAK,CAAC,gCAAgC,CAAC,CAAC;IACtD,CAAC;AACL,CAAC;AAED,SAAS,iBAAiB,CAAC,KAAuB;IAC9C,IAAI,CAAC,KAAK,CAAC,aAAa,EAAE,CAAC;QACvB,MAAM,IAAI,KAAK,CAAC,oCAAoC,CAAC,CAAC;IAC1D,CAAC;AACL,CAAC;AAED,SAAgB,eAAe,CAAC,QAAwB,EAAE,GAAkB;IACxE,MAAM,OAAO,GAA2B,EAAE,IAAI,EAAE,QAAQ,EAAE,MAAM,EAAE,cAAc,CAAC,QAAQ,EAAE,GAAG,CAAC,EAAE,CAAC;IAClG,MAAM,QAAQ,GAAG,GAAG,CAAC,WAAW,IAAI,GAAG,CAAC,WAAW,KAAK,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,WAAW,CAAC,CAAC,CAAC,EAAE,CAAC;IACxF,IAAI,CAAC,QAAQ,EAAE,CAAC;QACZ,OAAO,OAAO,CAAC,MAAM,CAAC;IAC1B,CAAC;IACD,IAAI,CAAC;QACD,OAAO,IAAI,sBAAW,CAAC,CAAC,OAAO,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,MAAM,EAAE,cAAc,CAAC,QAAQ,EAAE,GAAG,CAAC,EAAE,CAAC,EAAE,GAAG,CAAC,GAAG,CAAC,CAAC;IAC1G,CAAC;IAAC,OAAO,CAAC,EAAE,CAAC;QACT,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC,4BAA4B,QAAQ,kBAAmB,CAAW,CAAC,OAAO,EAAE,CAAC,CAAC;QAC3F,OAAO,OAAO,CAAC,MAAM,CAAC;IAC1B,CAAC;AACL,CAAC;AAED,SAAS,cAAc,CAAC,QAAwB,EAAE,GAAkB;IAChE,QAAQ,QAAQ,EAAE,CAAC;QACf,KAAK,OAAO;YACR,YAAY,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACxB,OAAO,IAAI,gBAAQ,CAAC,GAAG,CAAC,KAAK,CAAC,QAAQ,EAAE,GAAG,CAAC,KAAK,CAAC,WAAW,CAAC,CAAC;QACnE,KAAK,KAAK;YACN,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACtB,OAAO,IAAI,YAAM,CAAC,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC;QACrC,KAAK,MAAM;YACP,OAAO,IAAI,cAAO,CAAC,GAAG,CAAC,OAAO,EAAE,GAAG,CAAC,SAAS,EAAE,GAAG,CAAC,GAAG,CAAC,CAAC;QAC5D,KAAK,YAAY;YACb,iBAAiB,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YAC7B,OAAO,IAAI,0BAAa,CAAC,GAAG,CAAC,KAAK,CAAC,aAAa,EAAE,GAAG,CAAC,kBAAkB,CAAC,CAAC;QAC9E,KAAK,OAAO;YACR,MAAM,IAAI,KAAK,CAAC,sDAAsD,CAAC,CAAC;QAC5E;YACI,IAAI,GAAG,CAAC,UAAU,EAAE,IAAI,EAAE,EAAE,CAAC;gBACzB,OAAO,IAAI,eAAS,CAAC,GAAG,CAAC,YAAY,IAAI,EAAE,EAAE,GAAG,CAAC,QAAQ,IAAI,SAAS,EAAE,GAAG,CAAC,UAAU,CAAC,CAAC;YAC5F,CAAC;YACD,aAAa,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACzB,OAAO,IAAI,eAAS,CAAC,GAAG,CAAC,KAAK,CAAC,SAAS,EAAE,GAAG,CAAC,QAAQ,IAAI,SAAS,CAAC,CAAC;IAC7E,CAAC;AACL,CAAC;AAED,SAAgB,eAAe,CAAC,QAAwB,EAAE,GAAkB;IACxE,sGAAsG;IACtG,iGAAiG;IACjG,MAAM,OAAO,GAA2B,EAAE,IAAI,EAAE,QAAQ,EAAE,MAAM,EAAE,SAAS,CAAC,QAAQ,EAAE,GAAG,CAAC,EAAE,CAAC;IAC7F,MAAM,QAAQ,GAAG,GAAG,CAAC,WAAW,IAAI,GAAG,CAAC,WAAW,KAAK,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,WAAW,CAAC,CAAC,CAAC,EAAE,CAAC;IACxF,IAAI,CAAC,QAAQ,EAAE,CAAC;QACZ,OAAO,OAAO,CAAC,MAAM,CAAC;IAC1B,CAAC;IACD,IAAI,CAAC;QACD,OAAO,IAAI,sBAAW,CAAC,CAAC,OAAO,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,MAAM,EAAE,SAAS,CAAC,QAAQ,EAAE,GAAG,CAAC,EAAE,CAAC,EAAE,GAAG,CAAC,GAAG,CAAC,CAAC;IACrG,CAAC;IAAC,OAAO,CAAC,EAAE,CAAC;QACT,sGAAsG;QACtG,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC,4BAA4B,QAAQ,kBAAmB,CAAW,CAAC,OAAO,EAAE,CAAC,CAAC;QAC3F,OAAO,OAAO,CAAC,MAAM,CAAC;IAC1B,CAAC;AACL,CAAC;AAED;;;GAGG;AACH,SAAS,SAAS,CAAC,QAAwB,EAAE,GAAkB;IAC3D,MAAM,KAAK,GACP,QAAQ,KAAK,OAAO;QAChB,CAAC,CAAC,GAAG,CAAC,MAAM,CAAC,KAAK;QAClB,CAAC,CAAC,QAAQ,KAAK,KAAK;YAClB,CAAC,CAAC,GAAG,CAAC,MAAM,CAAC,GAAG;YAChB,CAAC,CAAC,QAAQ,KAAK,OAAO;gBACpB,CAAC,CAAC,GAAG,CAAC,MAAM,CAAC,KAAK;gBAClB,CAAC,CAAC,QAAQ,KAAK,YAAY;oBACzB,CAAC,CAAC,GAAG,GAAG,CAAC,kBAAkB,IAAI,yCAA4B,IAAI,GAAG,CAAC,MAAM,CAAC,UAAU,EAAE;oBACtF,CAAC,CAAC,GAAG,CAAC,MAAM,CAAC,MAAM,CAAC;IAClC,MAAM,GAAG,GAAG,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,OAAO,EAAE,UAAU,EAAE,GAAG,QAAQ,IAAI,CAAC,KAAK,IAAI,SAAS,CAAC,CAAC,OAAO,CAAC,UAAU,EAAE,GAAG,CAAC,EAAE,CAAC,CAAC;IAC/G,OAAO,IAAI,oBAAS,CAAC,cAAc,CAAC,QAAQ,EAAE,GAAG,CAAC,EAAE,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,GAAG,EAAE,QAAQ,EAAE,GAAG,CAAC,WAAW,EAAE,CAAC,CAAC;AAC1G,CAAC;AAED,SAAS,cAAc,CAAC,QAAwB,EAAE,GAAkB;IAChE,QAAQ,QAAQ,EAAE,CAAC;QACf,KAAK,OAAO;YACR,YAAY,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACxB,OAAO,IAAI,gBAAQ,CAAC,GAAG,CAAC,KAAK,CAAC,QAAQ,EAAE,GAAG,CAAC,KAAK,CAAC,WAAW,EAAE,GAAG,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC;QACrF,KAAK,KAAK;YACN,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACtB,OAAO,IAAI,YAAM,CAAC,GAAG,CAAC,KAAK,CAAC,GAAG,EAAE,GAAG,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;QACrD,KAAK,OAAO;YACR,OAAO,IAAI,gBAAQ,CAAC,GAAG,CAAC,OAAO,EAAE,GAAG,CAAC,MAAM,CAAC,KAAK,EAAE,GAAG,CAAC,GAAG,CAAC,CAAC;QAChE,KAAK,MAAM;YACP,MAAM,IAAI,KAAK,CAAC,qDAAqD,CAAC,CAAC;QAC3E,KAAK,YAAY;YACb,iBAAiB,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YAC7B,OAAO,IAAI,0BAAa,CACpB,GAAG,CAAC,KAAK,CAAC,aAAa,EACvB,GAAG,CAAC,kBAAkB,EACtB,GAAG,CAAC,MAAM,CAAC,UAAU,EACrB,GAAG,CAAC,WAAW,CAClB,CAAC;QACN;YACI,aAAa,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACzB,OAAO,IAAI,eAAS,CAChB,GAAG,CAAC,KAAK,CAAC,SAAS,EACnB,CAAC,GAAG,CAAC,MAAM,CAAC,MAAM,IAAI,OAAO,CAAgB,EAC7C,GAAG,CAAC,QAAQ,IAAI,SAAS,CAC5B,CAAC;IACV,CAAC;AACL,CAAC;AAED,uDAAuD;AACvD,MAAM,aAAa,GAAG,CAAC,OAAO,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,MAAM,EAAE,SAAS,CAAC,CAAC;AAE5E,sFAAsF;AAC/E,KAAK,UAAU,UAAU,CAAC,QAAwB,EAAE,GAAkB,EAAE,QAAgB;IAC3F,QAAQ,QAAQ,EAAE,CAAC;QACf,KAAK,OAAO;YACR,YAAY,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACxB,OAAO,IAAA,uBAAe,EAAC,GAAG,CAAC,KAAK,CAAC,QAAQ,EAAE,GAAG,CAAC,KAAK,CAAC,WAAW,EAAE,IAAA,kBAAW,EAAC,QAAQ,CAAC,CAAC,CAAC;QAC7F,KAAK,KAAK;YACN,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;YACtB,OAAO,IAAA,qBAAe,EAAC,GAAG,CAAC,KAAK,CAAC,GAAG,EAAE,IAAA,kBAAW,EAAC,QAAQ,CAAC,CAAC,CAAC;QACjE,KAAK,OAAO;YACR,OAAO,IAAA,uBAAe,GAAE,CAAC;QAC7B,KAAK,YAAY,CAAC,CAAC,CAAC;YAChB,6DAA6D;YAC7D,MAAM,KAAK,GAAG,GAAG,CAAC,kBAAkB,IAAI,yCAA4B,CAAC;YACrE,MAAM,MAAM,GAAG,MAAM,IAAA,uCAA0B,EAAC,QAAQ,CAAC,CAAC;YAC1D,OAAO,IAAA,8BAAiB,EAAC,MAAM,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,KAAK,CAAC,EAAE,MAAM,IAAI,EAAE,EAAE,QAAQ,CAAC,CAAC;QACvF,CAAC;QACD;YACI,OAAO,aAAa,CAAC;IAC7B,CAAC;AACL,CAAC;AAED,kHAAkH;AAC3G,KAAK,UAAU,aAAa,CAAC,QAAwB,EAAE,QAAgB;IAC1E,IAAI,QAAQ,KAAK,YAAY,EAAE,CAAC;QAC5B,OAAO,CAAC,MAAM,IAAA,uCAA0B,EAAC,eAAe,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;IAC9E,CAAC;IACD,OAAO,QAAQ,KAAK,MAAM,CAAC,CAAC,CAAC,IAAA,qBAAc,EAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;AAC/D,CAAC;AAED,8FAA8F;AACvF,KAAK,UAAU,aAAa,CAAC,QAAwB;IACxD,OAAO,QAAQ,KAAK,YAAY,CAAC,CAAC,CAAC,CAAC,MAAM,IAAA,uCAA0B,EAAC,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;AACxG,CAAC","sourcesContent":["/**\n * Factory that builds the configured STT/TTS engine. Cloud engines (OpenAI/Azure/AWS) use resolved\n * credentials; local engines (Vosk/Piper) download their models on demand into the data dir.\n * Adding a provider = one new engine class + one `case` here.\n */\nimport { OpenAiStt, type SttEngine } from './stt';\nimport { OpenAiTts, type OpenAiVoice, type TtsEngine } from './tts';\nimport { AzureStt, AzureTts, listAzureVoices } from './azure';\nimport { AwsStt, AwsTts, listPollyVoices, type AwsCreds } from './aws';\nimport { VoskStt, listVoskModels } from './vosk';\nimport { PiperTts, listPiperVoices } from './piper';\nimport {\n    OpenRouterStt,\n    OpenRouterTts,\n    listOpenRouterSpeechModels,\n    voicesForLanguage,\n    DEFAULT_OPENROUTER_TTS_MODEL,\n    type AudioDecoder,\n} from './openrouter';\nimport * as path from 'node:path';\n\nimport { CachedTts } from './ttsCache';\nimport { FallbackStt, FallbackTts, type NamedEngine } from './fallback';\nimport { isoToLocale } from './lang';\nimport type { VoiceLogger } from './download';\n\nexport type SpeechProvider = 'openai' | 'openrouter' | 'azure' | 'aws' | 'vosk' | 'piper';\n\n/** All speech credentials, resolved from config (or the central credential store). */\nexport interface VoiceCredentials {\n    openaiKey: string;\n    openrouterKey: string;\n    azureKey: string;\n    azureRegion: string;\n    aws: AwsCreds;\n}\n\n/** Provider-specific voice ids (each provider names voices differently). */\nexport interface VoiceNames {\n    openai: string; // alloy/echo/…\n    azure: string; // e.g. de-DE-KatjaNeural\n    aws: string; // e.g. Vicki\n    piper: string; // e.g. de_DE-thorsten-medium\n    openrouter: string; // depends on the model, e.g. Kore, george\n}\n\n/** Everything the factory needs to build any engine. */\nexport interface EngineContext {\n    creds: VoiceCredentials;\n    voices: VoiceNames;\n    /** Optional second engine, used when the primary one fails ('' = none). */\n    sttFallback?: SpeechProvider | '';\n    ttsFallback?: SpeechProvider | '';\n    /** Writable instance data dir (for the local engines' downloads). */\n    dataDir: string;\n    log: VoiceLogger;\n    /** Local model overrides ('' → default per language). */\n    voskModel: string;\n    /** OpenAI STT model ('' → 'whisper-1'; e.g. 'gpt-4o-transcribe'). */\n    sttModel: string;\n    /**\n     * OpenAI-compatible transcription server instead of OpenAI ('' = OpenAI), e.g. a local whisper container.\n     * It gets `sttServerKey`, never the OpenAI key — that one is only for OpenAI.\n     */\n    sttBaseUrl?: string;\n    /** Key for `sttBaseUrl` ('' = the server needs none). */\n    sttServerKey?: string;\n    /** OpenAI TTS model ('' → 'tts-1'; e.g. 'gpt-4o-mini-tts'). */\n    ttsModel: string;\n    /** OpenRouter models ('' → the defaults of openrouter.ts) */\n    openrouterSttModel: string;\n    openrouterTtsModel: string;\n    /** Decoder for compressed speech (OpenRouter models that only return mp3); absent → those models fail */\n    decodeAudio?: AudioDecoder;\n    /** Longest text that is spoken, in characters; longer ones are cut at a sentence end. 0 = no limit, absent = 400. */\n    ttsMaxChars?: number;\n}\n\nfunction requireAzure(creds: VoiceCredentials): void {\n    if (!creds.azureKey || !creds.azureRegion) {\n        throw new Error('Azure speech needs a subscription key and region');\n    }\n}\n\nfunction requireAws(creds: VoiceCredentials): void {\n    if (!creds.aws.accessKeyId || !creds.aws.secretAccessKey || !creds.aws.region) {\n        throw new Error('AWS speech needs an access key id, secret access key and region');\n    }\n}\n\nfunction requireOpenAi(creds: VoiceCredentials): void {\n    if (!creds.openaiKey) {\n        throw new Error('OpenAI speech needs an API key');\n    }\n}\n\nfunction requireOpenRouter(creds: VoiceCredentials): void {\n    if (!creds.openrouterKey) {\n        throw new Error('OpenRouter speech needs an API key');\n    }\n}\n\nexport function createSttEngine(provider: SpeechProvider, ctx: EngineContext): SttEngine {\n    const primary: NamedEngine<SttEngine> = { name: provider, engine: buildSttEngine(provider, ctx) };\n    const fallback = ctx.sttFallback && ctx.sttFallback !== provider ? ctx.sttFallback : '';\n    if (!fallback) {\n        return primary.engine;\n    }\n    try {\n        return new FallbackStt([primary, { name: fallback, engine: buildSttEngine(fallback, ctx) }], ctx.log);\n    } catch (e) {\n        ctx.log.warn(`Speech-to-text fallback '${fallback}' unavailable: ${(e as Error).message}`);\n        return primary.engine;\n    }\n}\n\nfunction buildSttEngine(provider: SpeechProvider, ctx: EngineContext): SttEngine {\n    switch (provider) {\n        case 'azure':\n            requireAzure(ctx.creds);\n            return new AzureStt(ctx.creds.azureKey, ctx.creds.azureRegion);\n        case 'aws':\n            requireAws(ctx.creds);\n            return new AwsStt(ctx.creds.aws);\n        case 'vosk':\n            return new VoskStt(ctx.dataDir, ctx.voskModel, ctx.log);\n        case 'openrouter':\n            requireOpenRouter(ctx.creds);\n            return new OpenRouterStt(ctx.creds.openrouterKey, ctx.openrouterSttModel);\n        case 'piper':\n            throw new Error('Piper is a text-to-speech engine, not speech-to-text');\n        default:\n            if (ctx.sttBaseUrl?.trim()) {\n                return new OpenAiStt(ctx.sttServerKey || '', ctx.sttModel || undefined, ctx.sttBaseUrl);\n            }\n            requireOpenAi(ctx.creds);\n            return new OpenAiStt(ctx.creds.openaiKey, ctx.sttModel || undefined);\n    }\n}\n\nexport function createTtsEngine(provider: SpeechProvider, ctx: EngineContext): TtsEngine {\n    // Each engine gets the shared behaviour (disk cache, length limit, SSML) and its own cache directory,\n    // so a fallback engine's voice can never be served later while the primary one is healthy again.\n    const primary: NamedEngine<TtsEngine> = { name: provider, engine: cachedTts(provider, ctx) };\n    const fallback = ctx.ttsFallback && ctx.ttsFallback !== provider ? ctx.ttsFallback : '';\n    if (!fallback) {\n        return primary.engine;\n    }\n    try {\n        return new FallbackTts([primary, { name: fallback, engine: cachedTts(fallback, ctx) }], ctx.log);\n    } catch (e) {\n        // A fallback that cannot even be built (missing key, wrong provider) must not take the main one down.\n        ctx.log.warn(`Text-to-speech fallback '${fallback}' unavailable: ${(e as Error).message}`);\n        return primary.engine;\n    }\n}\n\n/**\n * One provider binding plus the shared cache/length/SSML layer. One cache directory per provider+voice —\n * a voice change must not serve audio in the old voice.\n */\nfunction cachedTts(provider: SpeechProvider, ctx: EngineContext): TtsEngine {\n    const voice =\n        provider === 'azure'\n            ? ctx.voices.azure\n            : provider === 'aws'\n              ? ctx.voices.aws\n              : provider === 'piper'\n                ? ctx.voices.piper\n                : provider === 'openrouter'\n                  ? `${ctx.openrouterTtsModel || DEFAULT_OPENROUTER_TTS_MODEL}-${ctx.voices.openrouter}`\n                  : ctx.voices.openai;\n    const dir = path.join(ctx.dataDir, 'ttscache', `${provider}-${(voice || 'default').replace(/[^\\w.-]/g, '_')}`);\n    return new CachedTts(buildTtsEngine(provider, ctx), { dir, log: ctx.log, maxChars: ctx.ttsMaxChars });\n}\n\nfunction buildTtsEngine(provider: SpeechProvider, ctx: EngineContext): TtsEngine {\n    switch (provider) {\n        case 'azure':\n            requireAzure(ctx.creds);\n            return new AzureTts(ctx.creds.azureKey, ctx.creds.azureRegion, ctx.voices.azure);\n        case 'aws':\n            requireAws(ctx.creds);\n            return new AwsTts(ctx.creds.aws, ctx.voices.aws);\n        case 'piper':\n            return new PiperTts(ctx.dataDir, ctx.voices.piper, ctx.log);\n        case 'vosk':\n            throw new Error('Vosk is a speech-to-text engine, not text-to-speech');\n        case 'openrouter':\n            requireOpenRouter(ctx.creds);\n            return new OpenRouterTts(\n                ctx.creds.openrouterKey,\n                ctx.openrouterTtsModel,\n                ctx.voices.openrouter,\n                ctx.decodeAudio,\n            );\n        default:\n            requireOpenAi(ctx.creds);\n            return new OpenAiTts(\n                ctx.creds.openaiKey,\n                (ctx.voices.openai || 'alloy') as OpenAiVoice,\n                ctx.ttsModel || undefined,\n            );\n    }\n}\n\n/** OpenAI TTS voices are a fixed set (no list API). */\nconst OPENAI_VOICES = ['alloy', 'echo', 'fable', 'onyx', 'nova', 'shimmer'];\n\n/** List the available TTS voices for a provider (for the settings voice dropdown). */\nexport async function listVoices(provider: SpeechProvider, ctx: EngineContext, language: string): Promise<string[]> {\n    switch (provider) {\n        case 'azure':\n            requireAzure(ctx.creds);\n            return listAzureVoices(ctx.creds.azureKey, ctx.creds.azureRegion, isoToLocale(language));\n        case 'aws':\n            requireAws(ctx.creds);\n            return listPollyVoices(ctx.creds.aws, isoToLocale(language));\n        case 'piper':\n            return listPiperVoices();\n        case 'openrouter': {\n            // public list, no key needed: the voices of the chosen model\n            const model = ctx.openrouterTtsModel || DEFAULT_OPENROUTER_TTS_MODEL;\n            const models = await listOpenRouterSpeechModels('speech');\n            return voicesForLanguage(models.find(m => m.id === model)?.voices || [], language);\n        }\n        default:\n            return OPENAI_VOICES;\n    }\n}\n\n/** Suggested STT model names for the settings dropdown: the local Vosk catalogue, or the models of OpenRouter. */\nexport async function listSttModels(provider: SpeechProvider, language: string): Promise<string[]> {\n    if (provider === 'openrouter') {\n        return (await listOpenRouterSpeechModels('transcription')).map(m => m.id);\n    }\n    return provider === 'vosk' ? listVoskModels(language) : [];\n}\n\n/** TTS model names for the settings dropdown — only OpenRouter has a choice worth listing. */\nexport async function listTtsModels(provider: SpeechProvider): Promise<string[]> {\n    return provider === 'openrouter' ? (await listOpenRouterSpeechModels('speech')).map(m => m.id) : [];\n}\n"]}

package/build/lib/voice/stt.js

@@ -36,6 +36,7 @@ Object.defineProperty(exports, "__esModule", { value: true });
 exports.OpenAiStt = void 0;
 exports.hintsToPrompt = hintsToPrompt;
 exports.pcmToWav = pcmToWav;
+exports.normalizeSttBaseUrl = normalizeSttBaseUrl;
 /**
  * Speech-to-text engines. V1 ships the cloud engine (OpenAI Whisper); local engines
  * (Vosk / whisper.cpp / Wyoming) plug in behind the same `SttEngine` interface later.
@@ -88,12 +89,43 @@ function pcmToWav(pcm, sampleRate, numChannels = 1) {
     header.writeUInt32LE(pcm.length, 40);
     return Buffer.concat([header, pcm]);
 }
-/** Cloud STT via the OpenAI transcription API (Whisper). */
+/**
+ * Base URL of an OpenAI-compatible transcription server as the SDK wants it. Practically every such server
+ * (speaches/faster-whisper-server, LocalAI, vLLM, Groq) serves `/v1/audio/transcriptions`, so an address typed
+ * without a path gets `/v1`; one with a path is taken as it is.
+ */
+function normalizeSttBaseUrl(raw) {
+    const url = raw.trim().replace(/\/+$/, '');
+    if (!url) {
+        return '';
+    }
+    try {
+        const parsed = new URL(url);
+        return parsed.pathname === '/' || parsed.pathname === '' ? `${url}/v1` : url;
+    }
+    catch {
+        throw new Error(`speech recognition base URL "${raw}" is not a URL (e.g. http://192.168.1.10:8000/v1)`);
+    }
+}
+/**
+ * STT via the OpenAI transcription API (Whisper) — or any server that speaks it, e.g. a local
+ * whisper-large-v3-turbo next to ioBroker (`baseUrl`).
+ */
 class OpenAiStt {
     client;
     model;
-    constructor(apiKey, model = 'whisper-1') {
-        this.client = new openai_1.default({ apiKey });
+    /**
+     * @param apiKey OpenAI key, or the key of the server at `baseUrl` ('' for a server without one)
+     * @param model model id; on an own server as that server names it
+     * @param baseUrl OpenAI-compatible server instead of api.openai.com ('' = OpenAI)
+     */
+    constructor(apiKey, model = 'whisper-1', baseUrl = '') {
+        const baseURL = normalizeSttBaseUrl(baseUrl);
+        this.client = baseURL
+            ? // The SDK refuses an empty key; a local server ignores it. A server that hangs must not hold the
+                // satellite for the SDK's default ten minutes.
+                new openai_1.default({ apiKey: apiKey || 'none', baseURL, timeout: 60_000, maxRetries: 1 })
+            : new openai_1.default({ apiKey });
         this.model = model;
     }
     async transcribe(pcm, sampleRate, lang, hints) {

package/build/lib/voice/stt.js.map

@@ -1 +1 @@
-{"version":3,"file":"stt.js","sourceRoot":"","sources":["../../../src/lib/voice/stt.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAwBA,sCAqBC;AAGD,4BAmBC;AAnED;;;GAGG;AACH,iDAAwC;AAgBxC;;;GAGG;AACH,SAAgB,aAAa,CAAC,KAA2B,EAAE,QAAQ,GAAG,GAAG;IACrE,IAAI,CAAC,KAAK,EAAE,MAAM,EAAE,CAAC;QACjB,OAAO,EAAE,CAAC;IACd,CAAC;IACD,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAC;IAC/B,MAAM,KAAK,GAAa,EAAE,CAAC;IAC3B,IAAI,GAAG,GAAG,CAAC,CAAC;IACZ,KAAK,MAAM,CAAC,IAAI,KAAK,EAAE,CAAC;QACpB,MAAM,IAAI,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC;QAC9B,MAAM,GAAG,GAAG,IAAI,CAAC,WAAW,EAAE,CAAC;QAC/B,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,EAAE,CAAC;YACzB,SAAS;QACb,CAAC;QACD,IAAI,GAAG,GAAG,IAAI,CAAC,MAAM,GAAG,CAAC,GAAG,QAAQ,EAAE,CAAC;YACnC,MAAM;QACV,CAAC;QACD,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;QACd,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACjB,GAAG,IAAI,IAAI,CAAC,MAAM,GAAG,CAAC,CAAC;IAC3B,CAAC;IACD,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AAC5B,CAAC;AAED,wGAAwG;AACxG,SAAgB,QAAQ,CAAC,GAAW,EAAE,UAAkB,EAAE,WAAW,GAAG,CAAC;IACrE,MAAM,aAAa,GAAG,EAAE,CAAC;IACzB,MAAM,UAAU,GAAG,CAAC,WAAW,GAAG,aAAa,CAAC,GAAG,CAAC,CAAC;IACrD,MAAM,QAAQ,GAAG,UAAU,GAAG,UAAU,CAAC;IACzC,MAAM,MAAM,GAAG,MAAM,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC;IAChC,MAAM,CAAC,KAAK,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC;IACxB,MAAM,CAAC,aAAa,CAAC,EAAE,GAAG,GAAG,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC;IACzC,MAAM,CAAC,KAAK,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC;IACxB,MAAM,CAAC,KAAK,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC;IACzB,MAAM,CAAC,aAAa,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,CAAC,qBAAqB;IACnD,MAAM,CAAC,aAAa,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,qBAAqB;IAClD,MAAM,CAAC,aAAa,CAAC,WAAW,EAAE,EAAE,CAAC,CAAC;IACtC,MAAM,CAAC,aAAa,CAAC,UAAU,EAAE,EAAE,CAAC,CAAC;IACrC,MAAM,CAAC,aAAa,CAAC,QAAQ,EAAE,EAAE,CAAC,CAAC;IACnC,MAAM,CAAC,aAAa,CAAC,UAAU,EAAE,EAAE,CAAC,CAAC;IACrC,MAAM,CAAC,aAAa,CAAC,aAAa,EAAE,EAAE,CAAC,CAAC;IACxC,MAAM,CAAC,KAAK,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC;IACzB,MAAM,CAAC,aAAa,CAAC,GAAG,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC;IACrC,OAAO,MAAM,CAAC,MAAM,CAAC,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,CAAC;AACxC,CAAC;AAED,4DAA4D;AAC5D,MAAa,SAAS;IACD,MAAM,CAAS;IACf,KAAK,CAAS;IAE/B,YAAY,MAAc,EAAE,KAAK,GAAG,WAAW;QAC3C,IAAI,CAAC,MAAM,GAAG,IAAI,gBAAM,CAAC,EAAE,MAAM,EAAE,CAAC,CAAC;QACrC,IAAI,CAAC,KAAK,GAAG,KAAK,CAAC;IACvB,CAAC;IAED,KAAK,CAAC,UAAU,CAAC,GAAW,EAAE,UAAkB,EAAE,IAAY,EAAE,KAAgB;QAC5E,MAAM,IAAI,GAAG,MAAM,IAAA,eAAM,EAAC,QAAQ,CAAC,GAAG,EAAE,UAAU,CAAC,EAAE,WAAW,EAAE,EAAE,IAAI,EAAE,WAAW,EAAE,CAAC,CAAC;QACzF,mGAAmG;QACnG,kFAAkF;QAClF,MAAM,MAAM,GAAG,aAAa,CAAC,KAAK,CAAC,CAAC;QACpC,MAAM,GAAG,GAAG,MAAM,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,cAAc,CAAC,MAAM,CAAC;YACtD,IAAI;YACJ,KAAK,EAAE,IAAI,CAAC,KAAK;YACjB,0FAA0F;YAC1F,QAAQ,EAAE,CAAC,IAAI,IAAI,EAAE,CAAC,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,IAAI,SAAS;YACjD,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,MAAM,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;SAChC,CAAC,CAAC;QACH,OAAO,CAAC,GAAG,CAAC,IAAI,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC;IACnC,CAAC;CACJ;AAvBD,8BAuBC","sourcesContent":["/**\n * Speech-to-text engines. V1 ships the cloud engine (OpenAI Whisper); local engines\n * (Vosk / whisper.cpp / Wyoming) plug in behind the same `SttEngine` interface later.\n */\nimport OpenAI, { toFile } from 'openai';\n\nexport interface SttEngine {\n    /**\n     * Transcribe raw mono 16-bit PCM. `lang` is an ISO-639-1 hint ('' = auto-detect).\n     *\n     * `hints` is an optional domain vocabulary (device / room / scene names …) to bias recognition toward,\n     * so the engine better transcribes those proper nouns. Only engines that support *soft* biasing use it\n     * (OpenAI Whisper `prompt`, Azure phrase list); engines where a word list would be a hard constraint or\n     * needs pre-registration (Vosk grammar, AWS custom vocabulary) ignore it.\n     */\n    transcribe(pcm: Buffer, sampleRate: number, lang: string, hints?: string[]): Promise<string>;\n    /** Optional warm-up (install/download engine + model for `lang`) so the first request isn't slow. */\n    prepare?(lang: string): Promise<void>;\n}\n\n/**\n * Join vocabulary hints into a Whisper `prompt` string (a soft bias toward these terms), de-duplicated and\n * length-bounded to stay within the model's ~224-token prompt budget. Returns '' when there are no hints.\n */\nexport function hintsToPrompt(hints: string[] | undefined, maxChars = 800): string {\n    if (!hints?.length) {\n        return '';\n    }\n    const seen = new Set<string>();\n    const parts: string[] = [];\n    let len = 0;\n    for (const h of hints) {\n        const term = (h || '').trim();\n        const key = term.toLowerCase();\n        if (!term || seen.has(key)) {\n            continue;\n        }\n        if (len + term.length + 2 > maxChars) {\n            break;\n        }\n        seen.add(key);\n        parts.push(term);\n        len += term.length + 2;\n    }\n    return parts.join(', ');\n}\n\n/** Wrap raw 16-bit-signed-LE PCM (mono, or interleaved stereo) into a minimal 44-byte WAV container. */\nexport function pcmToWav(pcm: Buffer, sampleRate: number, numChannels = 1): Buffer {\n    const bitsPerSample = 16;\n    const blockAlign = (numChannels * bitsPerSample) / 8;\n    const byteRate = sampleRate * blockAlign;\n    const header = Buffer.alloc(44);\n    header.write('RIFF', 0);\n    header.writeUInt32LE(36 + pcm.length, 4);\n    header.write('WAVE', 8);\n    header.write('fmt ', 12);\n    header.writeUInt32LE(16, 16); // PCM fmt chunk size\n    header.writeUInt16LE(1, 20); // audio format = PCM\n    header.writeUInt16LE(numChannels, 22);\n    header.writeUInt32LE(sampleRate, 24);\n    header.writeUInt32LE(byteRate, 28);\n    header.writeUInt16LE(blockAlign, 32);\n    header.writeUInt16LE(bitsPerSample, 34);\n    header.write('data', 36);\n    header.writeUInt32LE(pcm.length, 40);\n    return Buffer.concat([header, pcm]);\n}\n\n/** Cloud STT via the OpenAI transcription API (Whisper). */\nexport class OpenAiStt implements SttEngine {\n    private readonly client: OpenAI;\n    private readonly model: string;\n\n    constructor(apiKey: string, model = 'whisper-1') {\n        this.client = new OpenAI({ apiKey });\n        this.model = model;\n    }\n\n    async transcribe(pcm: Buffer, sampleRate: number, lang: string, hints?: string[]): Promise<string> {\n        const file = await toFile(pcmToWav(pcm, sampleRate), 'audio.wav', { type: 'audio/wav' });\n        // A prompt biases Whisper toward the given domain vocabulary (device/room names) without excluding\n        // other words — improves recognition of proper nouns the NLU then needs to match.\n        const prompt = hintsToPrompt(hints);\n        const res = await this.client.audio.transcriptions.create({\n            file,\n            model: this.model,\n            // Whisper wants the bare ISO-639-1 code; strip any region (de-DE → de). '' → auto-detect.\n            language: (lang || '').split('-')[0] || undefined,\n            ...(prompt ? { prompt } : {}),\n        });\n        return (res.text || '').trim();\n    }\n}\n"]}
+{"version":3,"file":"stt.js","sourceRoot":"","sources":["../../../src/lib/voice/stt.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAwBA,sCAqBC;AAGD,4BAmBC;AAOD,kDAWC;AArFD;;;GAGG;AACH,iDAAwC;AAgBxC;;;GAGG;AACH,SAAgB,aAAa,CAAC,KAA2B,EAAE,QAAQ,GAAG,GAAG;IACrE,IAAI,CAAC,KAAK,EAAE,MAAM,EAAE,CAAC;QACjB,OAAO,EAAE,CAAC;IACd,CAAC;IACD,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAC;IAC/B,MAAM,KAAK,GAAa,EAAE,CAAC;IAC3B,IAAI,GAAG,GAAG,CAAC,CAAC;IACZ,KAAK,MAAM,CAAC,IAAI,KAAK,EAAE,CAAC;QACpB,MAAM,IAAI,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC;QAC9B,MAAM,GAAG,GAAG,IAAI,CAAC,WAAW,EAAE,CAAC;QAC/B,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,EAAE,CAAC;YACzB,SAAS;QACb,CAAC;QACD,IAAI,GAAG,GAAG,IAAI,CAAC,MAAM,GAAG,CAAC,GAAG,QAAQ,EAAE,CAAC;YACnC,MAAM;QACV,CAAC;QACD,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;QACd,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACjB,GAAG,IAAI,IAAI,CAAC,MAAM,GAAG,CAAC,CAAC;IAC3B,CAAC;IACD,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AAC5B,CAAC;AAED,wGAAwG;AACxG,SAAgB,QAAQ,CAAC,GAAW,EAAE,UAAkB,EAAE,WAAW,GAAG,CAAC;IACrE,MAAM,aAAa,GAAG,EAAE,CAAC;IACzB,MAAM,UAAU,GAAG,CAAC,WAAW,GAAG,aAAa,CAAC,GAAG,CAAC,CAAC;IACrD,MAAM,QAAQ,GAAG,UAAU,GAAG,UAAU,CAAC;IACzC,MAAM,MAAM,GAAG,MAAM,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC;IAChC,MAAM,CAAC,KAAK,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC;IACxB,MAAM,CAAC,aAAa,CAAC,EAAE,GAAG,GAAG,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC;IACzC,MAAM,CAAC,KAAK,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC;IACxB,MAAM,CAAC,KAAK,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC;IACzB,MAAM,CAAC,aAAa,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,CAAC,qBAAqB;IACnD,MAAM,CAAC,aAAa,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,qBAAqB;IAClD,MAAM,CAAC,aAAa,CAAC,WAAW,EAAE,EAAE,CAAC,CAAC;IACtC,MAAM,CAAC,aAAa,CAAC,UAAU,EAAE,EAAE,CAAC,CAAC;IACrC,MAAM,CAAC,aAAa,CAAC,QAAQ,EAAE,EAAE,CAAC,CAAC;IACnC,MAAM,CAAC,aAAa,CAAC,UAAU,EAAE,EAAE,CAAC,CAAC;IACrC,MAAM,CAAC,aAAa,CAAC,aAAa,EAAE,EAAE,CAAC,CAAC;IACxC,MAAM,CAAC,KAAK,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC;IACzB,MAAM,CAAC,aAAa,CAAC,GAAG,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC;IACrC,OAAO,MAAM,CAAC,MAAM,CAAC,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,CAAC;AACxC,CAAC;AAED;;;;GAIG;AACH,SAAgB,mBAAmB,CAAC,GAAW;IAC3C,MAAM,GAAG,GAAG,GAAG,CAAC,IAAI,EAAE,CAAC,OAAO,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC;IAC3C,IAAI,CAAC,GAAG,EAAE,CAAC;QACP,OAAO,EAAE,CAAC;IACd,CAAC;IACD,IAAI,CAAC;QACD,MAAM,MAAM,GAAG,IAAI,GAAG,CAAC,GAAG,CAAC,CAAC;QAC5B,OAAO,MAAM,CAAC,QAAQ,KAAK,GAAG,IAAI,MAAM,CAAC,QAAQ,KAAK,EAAE,CAAC,CAAC,CAAC,GAAG,GAAG,KAAK,CAAC,CAAC,CAAC,GAAG,CAAC;IACjF,CAAC;IAAC,MAAM,CAAC;QACL,MAAM,IAAI,KAAK,CAAC,gCAAgC,GAAG,mDAAmD,CAAC,CAAC;IAC5G,CAAC;AACL,CAAC;AAED;;;GAGG;AACH,MAAa,SAAS;IACD,MAAM,CAAS;IACf,KAAK,CAAS;IAE/B;;;;OAIG;IACH,YAAY,MAAc,EAAE,KAAK,GAAG,WAAW,EAAE,OAAO,GAAG,EAAE;QACzD,MAAM,OAAO,GAAG,mBAAmB,CAAC,OAAO,CAAC,CAAC;QAC7C,IAAI,CAAC,MAAM,GAAG,OAAO;YACjB,CAAC,CAAC,iGAAiG;gBACjG,+CAA+C;gBAC/C,IAAI,gBAAM,CAAC,EAAE,MAAM,EAAE,MAAM,IAAI,MAAM,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM,EAAE,UAAU,EAAE,CAAC,EAAE,CAAC;YACnF,CAAC,CAAC,IAAI,gBAAM,CAAC,EAAE,MAAM,EAAE,CAAC,CAAC;QAC7B,IAAI,CAAC,KAAK,GAAG,KAAK,CAAC;IACvB,CAAC;IAED,KAAK,CAAC,UAAU,CAAC,GAAW,EAAE,UAAkB,EAAE,IAAY,EAAE,KAAgB;QAC5E,MAAM,IAAI,GAAG,MAAM,IAAA,eAAM,EAAC,QAAQ,CAAC,GAAG,EAAE,UAAU,CAAC,EAAE,WAAW,EAAE,EAAE,IAAI,EAAE,WAAW,EAAE,CAAC,CAAC;QACzF,mGAAmG;QACnG,kFAAkF;QAClF,MAAM,MAAM,GAAG,aAAa,CAAC,KAAK,CAAC,CAAC;QACpC,MAAM,GAAG,GAAG,MAAM,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,cAAc,CAAC,MAAM,CAAC;YACtD,IAAI;YACJ,KAAK,EAAE,IAAI,CAAC,KAAK;YACjB,0FAA0F;YAC1F,QAAQ,EAAE,CAAC,IAAI,IAAI,EAAE,CAAC,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,IAAI,SAAS;YACjD,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,MAAM,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;SAChC,CAAC,CAAC;QACH,OAAO,CAAC,GAAG,CAAC,IAAI,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC;IACnC,CAAC;CACJ;AAjCD,8BAiCC","sourcesContent":["/**\n * Speech-to-text engines. V1 ships the cloud engine (OpenAI Whisper); local engines\n * (Vosk / whisper.cpp / Wyoming) plug in behind the same `SttEngine` interface later.\n */\nimport OpenAI, { toFile } from 'openai';\n\nexport interface SttEngine {\n    /**\n     * Transcribe raw mono 16-bit PCM. `lang` is an ISO-639-1 hint ('' = auto-detect).\n     *\n     * `hints` is an optional domain vocabulary (device / room / scene names …) to bias recognition toward,\n     * so the engine better transcribes those proper nouns. Only engines that support *soft* biasing use it\n     * (OpenAI Whisper `prompt`, Azure phrase list); engines where a word list would be a hard constraint or\n     * needs pre-registration (Vosk grammar, AWS custom vocabulary) ignore it.\n     */\n    transcribe(pcm: Buffer, sampleRate: number, lang: string, hints?: string[]): Promise<string>;\n    /** Optional warm-up (install/download engine + model for `lang`) so the first request isn't slow. */\n    prepare?(lang: string): Promise<void>;\n}\n\n/**\n * Join vocabulary hints into a Whisper `prompt` string (a soft bias toward these terms), de-duplicated and\n * length-bounded to stay within the model's ~224-token prompt budget. Returns '' when there are no hints.\n */\nexport function hintsToPrompt(hints: string[] | undefined, maxChars = 800): string {\n    if (!hints?.length) {\n        return '';\n    }\n    const seen = new Set<string>();\n    const parts: string[] = [];\n    let len = 0;\n    for (const h of hints) {\n        const term = (h || '').trim();\n        const key = term.toLowerCase();\n        if (!term || seen.has(key)) {\n            continue;\n        }\n        if (len + term.length + 2 > maxChars) {\n            break;\n        }\n        seen.add(key);\n        parts.push(term);\n        len += term.length + 2;\n    }\n    return parts.join(', ');\n}\n\n/** Wrap raw 16-bit-signed-LE PCM (mono, or interleaved stereo) into a minimal 44-byte WAV container. */\nexport function pcmToWav(pcm: Buffer, sampleRate: number, numChannels = 1): Buffer {\n    const bitsPerSample = 16;\n    const blockAlign = (numChannels * bitsPerSample) / 8;\n    const byteRate = sampleRate * blockAlign;\n    const header = Buffer.alloc(44);\n    header.write('RIFF', 0);\n    header.writeUInt32LE(36 + pcm.length, 4);\n    header.write('WAVE', 8);\n    header.write('fmt ', 12);\n    header.writeUInt32LE(16, 16); // PCM fmt chunk size\n    header.writeUInt16LE(1, 20); // audio format = PCM\n    header.writeUInt16LE(numChannels, 22);\n    header.writeUInt32LE(sampleRate, 24);\n    header.writeUInt32LE(byteRate, 28);\n    header.writeUInt16LE(blockAlign, 32);\n    header.writeUInt16LE(bitsPerSample, 34);\n    header.write('data', 36);\n    header.writeUInt32LE(pcm.length, 40);\n    return Buffer.concat([header, pcm]);\n}\n\n/**\n * Base URL of an OpenAI-compatible transcription server as the SDK wants it. Practically every such server\n * (speaches/faster-whisper-server, LocalAI, vLLM, Groq) serves `/v1/audio/transcriptions`, so an address typed\n * without a path gets `/v1`; one with a path is taken as it is.\n */\nexport function normalizeSttBaseUrl(raw: string): string {\n    const url = raw.trim().replace(/\\/+$/, '');\n    if (!url) {\n        return '';\n    }\n    try {\n        const parsed = new URL(url);\n        return parsed.pathname === '/' || parsed.pathname === '' ? `${url}/v1` : url;\n    } catch {\n        throw new Error(`speech recognition base URL \"${raw}\" is not a URL (e.g. http://192.168.1.10:8000/v1)`);\n    }\n}\n\n/**\n * STT via the OpenAI transcription API (Whisper) — or any server that speaks it, e.g. a local\n * whisper-large-v3-turbo next to ioBroker (`baseUrl`).\n */\nexport class OpenAiStt implements SttEngine {\n    private readonly client: OpenAI;\n    private readonly model: string;\n\n    /**\n     * @param apiKey OpenAI key, or the key of the server at `baseUrl` ('' for a server without one)\n     * @param model model id; on an own server as that server names it\n     * @param baseUrl OpenAI-compatible server instead of api.openai.com ('' = OpenAI)\n     */\n    constructor(apiKey: string, model = 'whisper-1', baseUrl = '') {\n        const baseURL = normalizeSttBaseUrl(baseUrl);\n        this.client = baseURL\n            ? // The SDK refuses an empty key; a local server ignores it. A server that hangs must not hold the\n              // satellite for the SDK's default ten minutes.\n              new OpenAI({ apiKey: apiKey || 'none', baseURL, timeout: 60_000, maxRetries: 1 })\n            : new OpenAI({ apiKey });\n        this.model = model;\n    }\n\n    async transcribe(pcm: Buffer, sampleRate: number, lang: string, hints?: string[]): Promise<string> {\n        const file = await toFile(pcmToWav(pcm, sampleRate), 'audio.wav', { type: 'audio/wav' });\n        // A prompt biases Whisper toward the given domain vocabulary (device/room names) without excluding\n        // other words — improves recognition of proper nouns the NLU then needs to match.\n        const prompt = hintsToPrompt(hints);\n        const res = await this.client.audio.transcriptions.create({\n            file,\n            model: this.model,\n            // Whisper wants the bare ISO-639-1 code; strip any region (de-DE → de). '' → auto-detect.\n            language: (lang || '').split('-')[0] || undefined,\n            ...(prompt ? { prompt } : {}),\n        });\n        return (res.text || '').trim();\n    }\n}\n"]}

package/build/main.js

@@ -107,6 +107,8 @@ const VOICE_FORM_FIELDS = [
     'voiceLanguage',
     'sttProvider',
     'sttModel',
+    'sttBaseUrl',
+    'sttServerKey',
     'openrouterSttModel',
     'voskModel',
     'ttsProvider',
@@ -131,7 +133,13 @@ const VOICE_FORM_FIELDS = [
     'piperVoice',
 ];
 /** Of those, the protected ones: the browser never gets them, so an empty value there means "keep the saved one" */
-const VOICE_FORM_SECRETS = ['voiceApiKey', 'openrouterSpeechKey', 'azureSpeechKey', 'awsSecretAccessKey'];
+const VOICE_FORM_SECRETS = [
+    'voiceApiKey',
+    'openrouterSpeechKey',
+    'azureSpeechKey',
+    'awsSecretAccessKey',
+    'sttServerKey',
+];
 /** An empty `ask` from the same caller is reported at most this often. */
 const EMPTY_ASK_REPORT_MS = 60_000;
 /** How long to wait for a device to confirm a write, and how often to look. */
@@ -700,6 +708,8 @@ class Assistant extends adapter_core_1.Adapter {
             log: this.log,
             voskModel: (cfg.voskModel || '').trim(),
             sttModel: (cfg.sttModel || '').trim(),
+            sttBaseUrl: (cfg.sttBaseUrl || '').trim(),
+            sttServerKey: cfg.sttServerKey || '',
             ttsModel: (cfg.ttsModel || '').trim(),
             openrouterSttModel: (cfg.openrouterSttModel || '').trim(),
             openrouterTtsModel: (cfg.openrouterTtsModel || '').trim(),
@@ -2941,6 +2951,7 @@ class Assistant extends adapter_core_1.Adapter {
                 fallback: cfg.sttFallback || undefined,
                 model: (provider === 'openrouter' ? cfg.openrouterSttModel : cfg.sttModel || cfg.voskModel || '').trim() ||
                     undefined,
+                server: (provider === 'openai' && cfg.sttBaseUrl?.trim()) || undefined,
                 language: cfg.voiceLanguage || this.language || '',
                 audioMs: origin.audioMs,
                 wakeWord: origin.wakeWord,