resolve conflicts with main

nanobot/providers/litellm_provider.py

@@ -53,6 +53,8 @@ class LiteLLMProvider(LLMProvider):
                 os.environ.setdefault("GEMINI_API_KEY", api_key)
             elif "zhipu" in default_model or "glm" in default_model or "zai" in default_model:
                 os.environ.setdefault("ZHIPUAI_API_KEY", api_key)
+            elif "groq" in default_model:
+                os.environ.setdefault("GROQ_API_KEY", api_key)
         
         if api_base:
             litellm.api_base = api_base
@@ -88,13 +90,13 @@ class LiteLLMProvider(LLMProvider):
             model = f"openrouter/{model}"
         
         # For Zhipu/Z.ai, ensure prefix is present
-        # Handle cases like "glm-4.7-flash" -> "zhipu/glm-4.7-flash"
+        # Handle cases like "glm-4.7-flash" -> "zai/glm-4.7-flash"
         if ("glm" in model.lower() or "zhipu" in model.lower()) and not (
             model.startswith("zhipu/") or 
             model.startswith("zai/") or 
             model.startswith("openrouter/")
         ):
-            model = f"zhipu/{model}"
+            model = f"zai/{model}"
         
         # For vLLM, use hosted_vllm/ prefix per LiteLLM docs
         # Convert openai/ prefix to hosted_vllm/ if user specified it

nanobot/providers/transcription.py

@@ -0,0 +1,65 @@
+"""Voice transcription provider using Groq."""
+
+import os
+from pathlib import Path
+from typing import Any
+
+import httpx
+from loguru import logger
+
+
+class GroqTranscriptionProvider:
+    """
+    Voice transcription provider using Groq's Whisper API.
+    
+    Groq offers extremely fast transcription with a generous free tier.
+    """
+    
+    def __init__(self, api_key: str | None = None):
+        self.api_key = api_key or os.environ.get("GROQ_API_KEY")
+        self.api_url = "https://api.groq.com/openai/v1/audio/transcriptions"
+    
+    async def transcribe(self, file_path: str | Path) -> str:
+        """
+        Transcribe an audio file using Groq.
+        
+        Args:
+            file_path: Path to the audio file.
+            
+        Returns:
+            Transcribed text.
+        """
+        if not self.api_key:
+            logger.warning("Groq API key not configured for transcription")
+            return ""
+        
+        path = Path(file_path)
+        if not path.exists():
+            logger.error(f"Audio file not found: {file_path}")
+            return ""
+        
+        try:
+            async with httpx.AsyncClient() as client:
+                with open(path, "rb") as f:
+                    files = {
+                        "file": (path.name, f),
+                        "model": (None, "whisper-large-v3"),
+                    }
+                    headers = {
+                        "Authorization": f"Bearer {self.api_key}",
+                    }
+                    
+                    response = await client.post(
+                        self.api_url,
+                        headers=headers,
+                        files=files,
+                        timeout=60.0
+                    )
+                    
+                    response.raise_for_status()
+                    data = response.json()
+                    return data.get("text", "")
+                    
+        except Exception as e:
+            logger.error(f"Groq transcription error: {e}")
+            return ""