fix: allow specifying transcription language

nanobot/channels/base.py

@@ -25,7 +25,7 @@ class BaseChannel(ABC):
     transcription_provider: str = "groq"
     transcription_api_key: str = ""
     transcription_api_base: str = ""
-    transcription_language: str = ""
+    transcription_language: str | None = None
 
     def __init__(self, config: Any, bus: MessageBus):
         """
@@ -49,6 +49,7 @@ class BaseChannel(ABC):
                 provider = OpenAITranscriptionProvider(
                     api_key=self.transcription_api_key,
                     api_base=self.transcription_api_base or None,
+                    language=self.transcription_language or None,
                 )
             else:
                 from nanobot.providers.transcription import GroqTranscriptionProvider

nanobot/channels/manager.py

@@ -63,6 +63,7 @@ class ChannelManager:
         transcription_provider = self.config.channels.transcription_provider
         transcription_key = self._resolve_transcription_key(transcription_provider)
         transcription_base = self._resolve_transcription_base(transcription_provider)
+        transcription_language = self.config.channels.transcription_language
 
         for name, cls in discover_all().items():
             section = getattr(self.config.channels, name, None)
@@ -88,7 +89,7 @@ class ChannelManager:
                 channel.transcription_provider = transcription_provider
                 channel.transcription_api_key = transcription_key
                 channel.transcription_api_base = transcription_base
-                channel.transcription_language = getattr(self.config.channels, "transcription_language", "")
+                channel.transcription_language = transcription_language
                 self.channels[name] = channel
                 logger.info("{} channel enabled", cls.display_name)
             except Exception as e:

nanobot/config/schema.py

@@ -29,7 +29,7 @@ class ChannelsConfig(Base):
     send_tool_hints: bool = False  # stream tool-call hints (e.g. read_file("…"))
     send_max_retries: int = Field(default=3, ge=0, le=10)  # Max delivery attempts (initial send included)
     transcription_provider: str = "groq"  # Voice transcription backend: "groq" or "openai"
-    transcription_language: str = ""  # Language code for Whisper STT (e.g. "en", "ru", "zh")
+    transcription_language: str | None = None  # Optional ISO-639-1 hint for audio transcription
 
 
 class DreamConfig(Base):

nanobot/providers/transcription.py

@@ -10,13 +10,19 @@ from loguru import logger
 class OpenAITranscriptionProvider:
     """Voice transcription provider using OpenAI's Whisper API."""
 
-    def __init__(self, api_key: str | None = None, api_base: str | None = None):
+    def __init__(
+        self,
+        api_key: str | None = None,
+        api_base: str | None = None,
+        language: str | None = None,
+    ):
         self.api_key = api_key or os.environ.get("OPENAI_API_KEY")
         self.api_url = (
             api_base
             or os.environ.get("OPENAI_TRANSCRIPTION_BASE_URL")
             or "https://api.openai.com/v1/audio/transcriptions"
         )
+        self.language = language
 
     async def transcribe(self, file_path: str | Path) -> str:
         if not self.api_key:
@@ -30,6 +36,8 @@ class OpenAITranscriptionProvider:
             async with httpx.AsyncClient() as client:
                 with open(path, "rb") as f:
                     files = {"file": (path.name, f), "model": (None, "whisper-1")}
+                    if self.language:
+                        files["language"] = (None, self.language)
                     headers = {"Authorization": f"Bearer {self.api_key}"}
                     response = await client.post(
                         self.api_url, headers=headers, files=files, timeout=60.0,
@@ -48,7 +56,12 @@ class GroqTranscriptionProvider:
     Groq offers extremely fast transcription with a generous free tier.
     """
 
-    def __init__(self, api_key: str | None = None, api_base: str | None = None, language: str | None = None):
+    def __init__(
+        self,
+        api_key: str | None = None,
+        api_base: str | None = None,
+        language: str | None = None,
+    ):
         self.api_key = api_key or os.environ.get("GROQ_API_KEY")
         self.api_url = api_base or os.environ.get("GROQ_BASE_URL") or "https://api.groq.com/openai/v1/audio/transcriptions"
         self.language = language