Merge PR #17: add voice transcription support with groq

README.md

@@ -60,6 +60,12 @@
 
 ## 📦 Install
 
+**Install with [uv](https://github.com/astral-sh/uv)** (recommended for speed)
+
+```bash
+uv tool install nanobot-ai
+```
+
 **Install from PyPi**
 
 ```bash
@@ -335,6 +341,7 @@ PRs welcome! The codebase is intentionally small and readable. 🤗
 
 **Roadmap** — Pick an item and [open a PR](https://github.com/HKUDS/nanobot/pulls)!
 
+- [x] **Voice Transcription** — Support for Groq Whisper (Issue #13)
 - [ ] **Multi-modal** — See and hear (images, voice, video)
 - [ ] **Long-term memory** — Never forget important context
 - [ ] **Better reasoning** — Multi-step planning and reflection

bridge/src/whatsapp.ts

@@ -160,6 +160,11 @@ export class WhatsAppClient {
       return `[Document] ${message.documentMessage.caption}`;
     }
 
+    // Voice/Audio message
+    if (message.audioMessage) {
+      return `[Voice Message]`;
+    }
+
     return null;
   }
 

nanobot/channels/manager.py

@@ -37,7 +37,9 @@ class ChannelManager:
             try:
                 from nanobot.channels.telegram import TelegramChannel
                 self.channels["telegram"] = TelegramChannel(
-                    self.config.channels.telegram, self.bus
+                    self.config.channels.telegram,
+                    self.bus,
+                    groq_api_key=self.config.providers.groq.api_key,
                 )
                 logger.info("Telegram channel enabled")
             except ImportError as e:

nanobot/channels/telegram.py

@@ -85,9 +85,10 @@ class TelegramChannel(BaseChannel):
     
     name = "telegram"
     
-    def __init__(self, config: TelegramConfig, bus: MessageBus):
+    def __init__(self, config: TelegramConfig, bus: MessageBus, groq_api_key: str = ""):
         super().__init__(config, bus)
         self.config: TelegramConfig = config
+        self.groq_api_key = groq_api_key
         self._app: Application | None = None
         self._chat_ids: dict[str, int] = {}  # Map sender_id to chat_id for replies
     
@@ -249,7 +250,20 @@ class TelegramChannel(BaseChannel):
                 await file.download_to_drive(str(file_path))
                 
                 media_paths.append(str(file_path))
-                content_parts.append(f"[{media_type}: {file_path}]")
+                
+                # Handle voice transcription
+                if media_type == "voice" or media_type == "audio":
+                    from nanobot.providers.transcription import GroqTranscriptionProvider
+                    transcriber = GroqTranscriptionProvider(api_key=self.groq_api_key)
+                    transcription = await transcriber.transcribe(file_path)
+                    if transcription:
+                        logger.info(f"Transcribed {media_type}: {transcription[:50]}...")
+                        content_parts.append(f"[transcription: {transcription}]")
+                    else:
+                        content_parts.append(f"[{media_type}: {file_path}]")
+                else:
+                    content_parts.append(f"[{media_type}: {file_path}]")
+                    
                 logger.debug(f"Downloaded {media_type} to {file_path}")
             except Exception as e:
                 logger.error(f"Failed to download media: {e}")

nanobot/channels/whatsapp.py

@@ -107,6 +107,11 @@ class WhatsAppChannel(BaseChannel):
             # Extract just the phone number as chat_id
             chat_id = sender.split("@")[0] if "@" in sender else sender
             
+            # Handle voice transcription if it's a voice message
+            if content == "[Voice Message]":
+                logger.info(f"Voice message received from {chat_id}, but direct download from bridge is not yet supported.")
+                content = "[Voice Message: Transcription not available for WhatsApp yet]"
+            
             await self._handle_message(
                 sender_id=chat_id,
                 chat_id=sender,  # Use full JID for replies

nanobot/config/schema.py

@@ -50,6 +50,7 @@ class ProvidersConfig(BaseModel):
     anthropic: ProviderConfig = Field(default_factory=ProviderConfig)
     openai: ProviderConfig = Field(default_factory=ProviderConfig)
     openrouter: ProviderConfig = Field(default_factory=ProviderConfig)
+    groq: ProviderConfig = Field(default_factory=ProviderConfig)
     zhipu: ProviderConfig = Field(default_factory=ProviderConfig)
     vllm: ProviderConfig = Field(default_factory=ProviderConfig)
     gemini: ProviderConfig = Field(default_factory=ProviderConfig)
@@ -91,13 +92,14 @@ class Config(BaseSettings):
         return Path(self.agents.defaults.workspace).expanduser()
     
     def get_api_key(self) -> str | None:
-        """Get API key in priority order: OpenRouter > Anthropic > OpenAI > Gemini > Zhipu > vLLM."""
+        """Get API key in priority order: OpenRouter > Anthropic > OpenAI > Gemini > Zhipu > Groq > vLLM."""
         return (
             self.providers.openrouter.api_key or
             self.providers.anthropic.api_key or
             self.providers.openai.api_key or
             self.providers.gemini.api_key or
             self.providers.zhipu.api_key or
+            self.providers.groq.api_key or
             self.providers.vllm.api_key or
             None
         )

nanobot/providers/litellm_provider.py

@@ -51,6 +51,8 @@ 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

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 ""