Initial commit of current state

apple_tts.py

@@ -0,0 +1,119 @@
+"""Text-to-speech using the macOS system voices.
+
+Drives the `say` binary rather than AVSpeechSynthesizer. `say` can render
+straight to signed 16-bit little-endian PCM at a chosen sample rate, which is
+exactly what the pipeline wants, and it avoids reading raw AVAudioPCMBuffer
+channel pointers through pyobjc.
+
+Note that Siri's voices are not reachable this way. Apple does not expose them
+to third-party apps; `say` and AVSpeechSynthesizer only see the voices listed
+under System Settings > Accessibility > Spoken Content.
+"""
+
+import asyncio
+import os
+import tempfile
+import wave
+from collections.abc import AsyncGenerator
+
+from loguru import logger
+
+from pipecat.audio.utils import create_stream_resampler
+from pipecat.frames.frames import ErrorFrame, Frame, TTSAudioRawFrame
+from pipecat.services.settings import TTSSettings
+from pipecat.services.tts_service import TTSService
+
+SAY = "/usr/bin/say"
+
+# Chunked so playback can start before the whole file is read.
+_CHUNK_FRAMES = 2400  # 100ms at 24kHz
+
+
+def available_voices() -> list[tuple[str, str]]:
+    """Return (name, language) for every installed system voice."""
+    import AVFoundation as AV
+
+    return [(v.name(), v.language()) for v in AV.AVSpeechSynthesisVoice.speechVoices()]
+
+
+def find_voice(name: str) -> tuple[str, str] | None:
+    """Look up an installed voice by name, case-insensitively."""
+    for voice_name, language in available_voices():
+        if voice_name.lower() == name.lower():
+            return voice_name, language
+    return None
+
+
+class AppleTTSService(TTSService):
+    """Speak text with a macOS system voice.
+
+    Args:
+        voice: An installed system voice name, e.g. "Moira" for Irish English.
+        rate_wpm: Speaking rate in words per minute. None uses the voice default.
+    """
+
+    def __init__(self, *, voice: str = "Moira", rate_wpm: int | None = None, **kwargs):
+        super().__init__(
+            push_start_frame=True,
+            push_stop_frames=True,
+            settings=TTSSettings(model=None, voice=voice, language=None),
+            **kwargs,
+        )
+        self._voice = voice
+        self._rate_wpm = rate_wpm
+        self._resampler = create_stream_resampler()
+
+        if find_voice(voice) is None:
+            names = ", ".join(sorted(n for n, _ in available_voices())[:8])
+            raise ValueError(
+                f"macOS has no voice named {voice!r}. Installed voices include: {names}…  "
+                "Add more under System Settings > Accessibility > Spoken Content > System Voice."
+            )
+
+    def can_generate_metrics(self) -> bool:
+        return True
+
+    async def run_tts(self, text: str, context_id: str) -> AsyncGenerator[Frame, None]:
+        """Synthesize one chunk of text."""
+        await self.start_tts_usage_metrics(text)
+
+        with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as f:
+            path = f.name
+        try:
+            command = [SAY, "-v", self._voice, "-o", path]
+            if self._rate_wpm:
+                command += ["-r", str(self._rate_wpm)]
+            command += [f"--data-format=LEI16@{self.sample_rate}", "--", text]
+
+            process = await asyncio.create_subprocess_exec(
+                *command,
+                stdout=asyncio.subprocess.DEVNULL,
+                stderr=asyncio.subprocess.PIPE,
+            )
+            _, stderr = await process.communicate()
+            if process.returncode != 0:
+                detail = stderr.decode(errors="replace").strip()
+                yield ErrorFrame(error=f"say failed ({process.returncode}): {detail}")
+                return
+
+            with wave.open(path, "rb") as wav:
+                source_rate = wav.getframerate()
+                while chunk := wav.readframes(_CHUNK_FRAMES):
+                    await self.stop_ttfb_metrics()
+                    if source_rate != self.sample_rate:
+                        chunk = await self._resampler.resample(
+                            chunk, source_rate, self.sample_rate
+                        )
+                    yield TTSAudioRawFrame(
+                        audio=chunk,
+                        sample_rate=self.sample_rate,
+                        num_channels=1,
+                        context_id=context_id,
+                    )
+        except Exception as e:
+            logger.exception(f"Apple TTS failed: {e}")
+            yield ErrorFrame(error=f"Apple TTS failed: {e}")
+        finally:
+            await self.stop_ttfb_metrics()
+            if os.path.exists(path):
+                os.unlink(path)