diff --git a/nanobot/channels/base.py b/nanobot/channels/base.py
index a59b31e2..778ed4d4 100644
--- a/nanobot/channels/base.py
+++ b/nanobot/channels/base.py
@@ -25,6 +25,7 @@ class BaseChannel(ABC):
     transcription_provider: str = "groq"
     transcription_api_key: str = ""
     transcription_api_base: str = ""
+    transcription_language: str = ""
 
     def __init__(self, config: Any, bus: MessageBus):
         """
@@ -54,6 +55,7 @@ class BaseChannel(ABC):
                 provider = GroqTranscriptionProvider(
                     api_key=self.transcription_api_key,
                     api_base=self.transcription_api_base or None,
+                    language=self.transcription_language or None,
                 )
             return await provider.transcribe(file_path)
         except Exception as e:
diff --git a/nanobot/channels/manager.py b/nanobot/channels/manager.py
index f8f2c1d8..0f0b7430 100644
--- a/nanobot/channels/manager.py
+++ b/nanobot/channels/manager.py
@@ -88,6 +88,7 @@ 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", "")
                 self.channels[name] = channel
                 logger.info("{} channel enabled", cls.display_name)
             except Exception as e:
diff --git a/nanobot/config/schema.py b/nanobot/config/schema.py
index ac48619f..a6978ba3 100644
--- a/nanobot/config/schema.py
+++ b/nanobot/config/schema.py
@@ -29,6 +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")
 
 
 class DreamConfig(Base):
diff --git a/nanobot/providers/transcription.py b/nanobot/providers/transcription.py
index 617fd3eb..daeedfbe 100644
--- a/nanobot/providers/transcription.py
+++ b/nanobot/providers/transcription.py
@@ -48,9 +48,10 @@ 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):
+    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
 
     async def transcribe(self, file_path: str | Path) -> str:
         """
@@ -78,6 +79,8 @@ class GroqTranscriptionProvider:
                         "file": (path.name, f),
                         "model": (None, "whisper-large-v3"),
                     }
+                    if self.language:
+                        files["language"] = (None, self.language)
                     headers = {
                         "Authorization": f"Bearer {self.api_key}",
                     }