diff --git a/nanobot/channels/base.py b/nanobot/channels/base.py index dd29c0851..27d0b07a8 100644 --- a/nanobot/channels/base.py +++ b/nanobot/channels/base.py @@ -24,6 +24,7 @@ class BaseChannel(ABC): display_name: str = "Base" transcription_provider: str = "groq" transcription_api_key: str = "" + _transcription_fallback_key: str = "" def __init__(self, config: Any, bus: MessageBus): """ @@ -38,19 +39,30 @@ class BaseChannel(ABC): self._running = False async def transcribe_audio(self, file_path: str | Path) -> str: - """Transcribe an audio file via Whisper (OpenAI or Groq). Returns empty string on failure.""" + """Transcribe an audio file via Whisper. Falls back to the other provider on failure.""" if not self.transcription_api_key: return "" + result = await self._try_transcribe(self.transcription_provider, self.transcription_api_key, file_path) + if result: + return result + fallback = "groq" if self.transcription_provider == "openai" else "openai" + if self._transcription_fallback_key: + logger.info("{}: trying {} fallback for transcription", self.name, fallback) + return await self._try_transcribe(fallback, self._transcription_fallback_key, file_path) + return "" + + async def _try_transcribe(self, provider: str, api_key: str, file_path: str | Path) -> str: + """Attempt transcription with a single provider. Returns empty string on failure.""" try: - if self.transcription_provider == "openai": + if provider == "openai": from nanobot.providers.transcription import OpenAITranscriptionProvider - provider = OpenAITranscriptionProvider(api_key=self.transcription_api_key) + p = OpenAITranscriptionProvider(api_key=api_key) else: from nanobot.providers.transcription import GroqTranscriptionProvider - provider = GroqTranscriptionProvider(api_key=self.transcription_api_key) - return await provider.transcribe(file_path) + p = GroqTranscriptionProvider(api_key=api_key) + return await p.transcribe(file_path) except Exception as e: - logger.warning("{}: audio transcription failed: {}", self.name, e) + logger.warning("{}: {} transcription failed: {}", self.name, provider, e) return "" async def login(self, force: bool = False) -> bool: diff --git a/nanobot/channels/manager.py b/nanobot/channels/manager.py index b52c38ca3..d7bb4ef2d 100644 --- a/nanobot/channels/manager.py +++ b/nanobot/channels/manager.py @@ -41,6 +41,8 @@ class ChannelManager: transcription_provider = self.config.channels.transcription_provider transcription_key = self._resolve_transcription_key(transcription_provider) + fallback_provider = "groq" if transcription_provider == "openai" else "openai" + fallback_key = self._resolve_transcription_key(fallback_provider) for name, cls in discover_all().items(): section = getattr(self.config.channels, name, None) @@ -57,6 +59,7 @@ class ChannelManager: channel = cls(section, self.bus) channel.transcription_provider = transcription_provider channel.transcription_api_key = transcription_key + channel._transcription_fallback_key = fallback_key self.channels[name] = channel logger.info("{} channel enabled", cls.display_name) except Exception as e: @@ -66,9 +69,12 @@ class ChannelManager: def _resolve_transcription_key(self, provider: str) -> str: """Pick the API key for the configured transcription provider.""" - if provider == "openai": - return self.config.providers.openai.api_key - return self.config.providers.groq.api_key + 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():