Voice Ai Engine Development

Audio In → Transcriber → Agent → Synthesizer → Audio Out
           (Worker 1)   (Worker 2)  (Worker 3)

class BaseWorker:
    def __init__(self, input_queue, output_queue):
        self.input_queue = input_queue   # asyncio.Queue to consume from
        self.output_queue = output_queue # asyncio.Queue to produce to
        self.active = False
    
    def start(self):
        """Start the worker's processing loop"""
        self.active = True
        asyncio.create_task(self._run_loop())
    
    async def _run_loop(self):
        """Main processing loop - runs forever until terminated"""
        while self.active:
            item = await self.input_queue.get()  # Block until item arrives
            await self.process(item)              # Process the item
    
    async def process(self, item):
        """Override this - does the actual work"""
        raise NotImplementedError
    
    def terminate(self):
        """Stop the worker"""
        self.active = False

class BaseTranscriber:
    def __init__(self, transcriber_config):
        self.input_queue = asyncio.Queue()   # Audio chunks (bytes)
        self.output_queue = asyncio.Queue()  # Transcriptions
        self.is_muted = False
    
    def send_audio(self, chunk: bytes):
        """Client calls this to send audio"""
        if not self.is_muted:
            self.input_queue.put_nowait(chunk)
        else:
            # Send silence instead (prevents echo during bot speech)
            self.input_queue.put_nowait(self.create_silent_chunk(len(chunk)))
    
    def mute(self):
        """Called when bot starts speaking (prevents echo)"""
        self.is_muted = True
    
    def unmute(self):
        """Called when bot stops speaking"""
        self.is_muted = False

class Transcription:
    message: str          # "Hello, how are you?"
    confidence: float     # 0.95
    is_final: bool        # True = complete sentence, False = partial
    is_interrupt: bool    # Set by TranscriptionsWorker