Merge PR #2530: feat: unify voice message transcription via OpenAI/Groq Whisper

feat: unify voice message transcription via OpenAI/Groq Whisper

README.md

@@ -900,7 +900,7 @@ IMAP_PASSWORD=your-password-here
 ### Providers
 
 > [!TIP]
-> - **Groq** provides free voice transcription via Whisper. If configured, Telegram voice messages will be automatically transcribed.
+> - **Voice transcription**: Voice messages (Telegram, WhatsApp) are automatically transcribed using Whisper. By default Groq is used (free tier). Set `"transcriptionProvider": "openai"` under `channels` to use OpenAI Whisper instead — the API key is picked from the matching provider config.
 > - **MiniMax Coding Plan**: Exclusive discount links for the nanobot community: [Overseas](https://platform.minimax.io/subscribe/coding-plan?code=9txpdXw04g&source=link) · [Mainland China](https://platform.minimaxi.com/subscribe/token-plan?code=GILTJpMTqZ&source=link)
 > - **MiniMax (Mainland China)**: If your API key is from MiniMax's mainland China platform (minimaxi.com), set `"apiBase": "https://api.minimaxi.com/v1"` in your minimax provider config.
 > - **VolcEngine / BytePlus Coding Plan**: Use dedicated providers `volcengineCodingPlan` or `byteplusCodingPlan` instead of the pay-per-use `volcengine` / `byteplus` providers.
@@ -916,9 +916,9 @@ IMAP_PASSWORD=your-password-here
 | `byteplus` | LLM (VolcEngine international, pay-per-use) | [Coding Plan](https://www.byteplus.com/en/activity/codingplan?utm_campaign=nanobot&utm_content=nanobot&utm_medium=devrel&utm_source=OWO&utm_term=nanobot) · [byteplus.com](https://www.byteplus.com) |
 | `anthropic` | LLM (Claude direct) | [console.anthropic.com](https://console.anthropic.com) |
 | `azure_openai` | LLM (Azure OpenAI) | [portal.azure.com](https://portal.azure.com) |
-| `openai` | LLM (GPT direct) | [platform.openai.com](https://platform.openai.com) |
+| `openai` | LLM + Voice transcription (Whisper) | [platform.openai.com](https://platform.openai.com) |
 | `deepseek` | LLM (DeepSeek direct) | [platform.deepseek.com](https://platform.deepseek.com) |
-| `groq` | LLM + **Voice transcription** (Whisper) | [console.groq.com](https://console.groq.com) |
+| `groq` | LLM + Voice transcription (Whisper, default) | [console.groq.com](https://console.groq.com) |
 | `minimax` | LLM (MiniMax direct) | [platform.minimaxi.com](https://platform.minimaxi.com) |
 | `gemini` | LLM (Gemini direct) | [aistudio.google.com](https://aistudio.google.com) |
 | `aihubmix` | LLM (API gateway, access to all models) | [aihubmix.com](https://aihubmix.com) |
@@ -1233,6 +1233,7 @@ Global settings that apply to all channels. Configure under the `channels` secti
     "sendProgress": true,
     "sendToolHints": false,
     "sendMaxRetries": 3,
+    "transcriptionProvider": "groq",
     "telegram": { ... }
   }
 }
@@ -1243,6 +1244,7 @@ Global settings that apply to all channels. Configure under the `channels` secti
 | `sendProgress` | `true` | Stream agent's text progress to the channel |
 | `sendToolHints` | `false` | Stream tool-call hints (e.g. `read_file("…")`) |
 | `sendMaxRetries` | `3` | Max delivery attempts per outbound message, including the initial send (0-10 configured, minimum 1 actual attempt) |
+| `transcriptionProvider` | `"groq"` | Voice transcription backend: `"groq"` (free tier, default) or `"openai"`. API key is auto-resolved from the matching provider config. |
 
 #### Retry Behavior
 

nanobot/channels/base.py

@@ -22,6 +22,7 @@ class BaseChannel(ABC):
 
     name: str = "base"
     display_name: str = "Base"
+    transcription_provider: str = "groq"
     transcription_api_key: str = ""
 
     def __init__(self, config: Any, bus: MessageBus):
@@ -37,13 +38,16 @@ class BaseChannel(ABC):
         self._running = False
 
     async def transcribe_audio(self, file_path: str | Path) -> str:
-        """Transcribe an audio file via Groq Whisper. Returns empty string on failure."""
+        """Transcribe an audio file via Whisper (OpenAI or Groq). Returns empty string on failure."""
         if not self.transcription_api_key:
             return ""
         try:
-            from nanobot.providers.transcription import GroqTranscriptionProvider
-
-            provider = GroqTranscriptionProvider(api_key=self.transcription_api_key)
+            if self.transcription_provider == "openai":
+                from nanobot.providers.transcription import OpenAITranscriptionProvider
+                provider = OpenAITranscriptionProvider(api_key=self.transcription_api_key)
+            else:
+                from nanobot.providers.transcription import GroqTranscriptionProvider
+                provider = GroqTranscriptionProvider(api_key=self.transcription_api_key)
             return await provider.transcribe(file_path)
         except Exception as e:
             logger.warning("{}: audio transcription failed: {}", self.name, e)

nanobot/channels/manager.py

@@ -39,7 +39,8 @@ class ChannelManager:
         """Initialize channels discovered via pkgutil scan + entry_points plugins."""
         from nanobot.channels.registry import discover_all
 
-        groq_key = self.config.providers.groq.api_key
+        transcription_provider = self.config.channels.transcription_provider
+        transcription_key = self._resolve_transcription_key(transcription_provider)
 
         for name, cls in discover_all().items():
             section = getattr(self.config.channels, name, None)
@@ -54,7 +55,8 @@ class ChannelManager:
                 continue
             try:
                 channel = cls(section, self.bus)
-                channel.transcription_api_key = groq_key
+                channel.transcription_provider = transcription_provider
+                channel.transcription_api_key = transcription_key
                 self.channels[name] = channel
                 logger.info("{} channel enabled", cls.display_name)
             except Exception as e:
@@ -62,6 +64,15 @@ class ChannelManager:
 
         self._validate_allow_from()
 
+    def _resolve_transcription_key(self, provider: str) -> str:
+        """Pick the API key for the configured transcription provider."""
+        try:
+            if provider == "openai":
+                return self.config.providers.openai.api_key
+            return self.config.providers.groq.api_key
+        except AttributeError:
+            return ""
+
     def _validate_allow_from(self) -> None:
         for name, ch in self.channels.items():
             if getattr(ch.config, "allow_from", None) == []:

nanobot/channels/whatsapp.py

@@ -232,17 +232,22 @@ class WhatsAppChannel(BaseChannel):
             sender_id = user_id.split("@")[0] if "@" in user_id else user_id
             logger.info("Sender {}", sender)
 
-            # Handle voice transcription if it's a voice message
-            if content == "[Voice Message]":
-                logger.info(
-                    "Voice message received from {}, but direct download from bridge is not yet supported.",
-                    sender_id,
-                )
-                content = "[Voice Message: Transcription not available for WhatsApp yet]"
-
             # Extract media paths (images/documents/videos downloaded by the bridge)
             media_paths = data.get("media") or []
 
+            # Handle voice transcription if it's a voice message
+            if content == "[Voice Message]":
+                if media_paths:
+                    logger.info("Transcribing voice message from {}...", sender_id)
+                    transcription = await self.transcribe_audio(media_paths[0])
+                    if transcription:
+                        content = transcription
+                        logger.info("Transcribed voice from {}: {}...", sender_id, transcription[:50])
+                    else:
+                        content = "[Voice Message: Transcription failed]"
+                else:
+                    content = "[Voice Message: Audio not available]"
+
             # Build content tags matching Telegram's pattern: [image: /path] or [file: /path]
             if media_paths:
                 for p in media_paths:

nanobot/config/schema.py

@@ -28,6 +28,7 @@ class ChannelsConfig(Base):
     send_progress: bool = True  # stream agent's text progress to the channel
     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"
 
 
 class DreamConfig(Base):

nanobot/providers/transcription.py

@@ -1,4 +1,4 @@
-"""Voice transcription provider using Groq."""
+"""Voice transcription providers (Groq and OpenAI Whisper)."""
 
 import os
 from pathlib import Path
@@ -7,6 +7,36 @@ import httpx
 from loguru import logger
 
 
+class OpenAITranscriptionProvider:
+    """Voice transcription provider using OpenAI's Whisper API."""
+
+    def __init__(self, api_key: str | None = None):
+        self.api_key = api_key or os.environ.get("OPENAI_API_KEY")
+        self.api_url = "https://api.openai.com/v1/audio/transcriptions"
+
+    async def transcribe(self, file_path: str | Path) -> str:
+        if not self.api_key:
+            logger.warning("OpenAI API key not configured for transcription")
+            return ""
+        path = Path(file_path)
+        if not path.exists():
+            logger.error("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-1")}
+                    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()
+                    return response.json().get("text", "")
+        except Exception as e:
+            logger.error("OpenAI transcription error: {}", e)
+            return ""
+
+
 class GroqTranscriptionProvider:
     """
     Voice transcription provider using Groq's Whisper API.

tests/channels/test_whatsapp_channel.py

@@ -163,6 +163,53 @@ async def test_group_policy_mention_accepts_mentioned_group_message():
     assert kwargs["sender_id"] == "user"
 
 
+@pytest.mark.asyncio
+async def test_voice_message_transcription_uses_media_path():
+    """Voice messages are transcribed when media path is available."""
+    ch = WhatsAppChannel({"enabled": True}, MagicMock())
+    ch.transcription_provider = "openai"
+    ch.transcription_api_key = "sk-test"
+    ch._handle_message = AsyncMock()
+    ch.transcribe_audio = AsyncMock(return_value="Hello world")
+
+    await ch._handle_bridge_message(
+        json.dumps({
+            "type": "message",
+            "id": "v1",
+            "sender": "12345@s.whatsapp.net",
+            "pn": "",
+            "content": "[Voice Message]",
+            "timestamp": 1,
+            "media": ["/tmp/voice.ogg"],
+        })
+    )
+
+    ch.transcribe_audio.assert_awaited_once_with("/tmp/voice.ogg")
+    kwargs = ch._handle_message.await_args.kwargs
+    assert kwargs["content"].startswith("Hello world")
+
+
+@pytest.mark.asyncio
+async def test_voice_message_no_media_shows_not_available():
+    """Voice messages without media produce a fallback placeholder."""
+    ch = WhatsAppChannel({"enabled": True}, MagicMock())
+    ch._handle_message = AsyncMock()
+
+    await ch._handle_bridge_message(
+        json.dumps({
+            "type": "message",
+            "id": "v2",
+            "sender": "12345@s.whatsapp.net",
+            "pn": "",
+            "content": "[Voice Message]",
+            "timestamp": 1,
+        })
+    )
+
+    kwargs = ch._handle_message.await_args.kwargs
+    assert kwargs["content"] == "[Voice Message: Audio not available]"
+
+
 def test_load_or_create_bridge_token_persists_generated_secret(tmp_path):
     token_path = tmp_path / "whatsapp-auth" / "bridge-token"