VoiceAgent/speech_analyzer_stt.py

"""Speech-to-text through macOS 26's SpeechAnalyzer, via a Swift helper.

`SpeechTranscriber` is the accurate recogniser on this OS, and it is Swift-only
— built on actors and AsyncSequence, with no Objective-C surface — so pyobjc
cannot reach it. `swift/speech-helper` is a small binary that does, and this
drives it as a subprocess: one process per utterance, JSON on stdout.

Two modules sit behind the analyzer and the choice between them is not obvious,
so it was measured on eight sentences of technical speech:

| module                            | WER   |
|-----------------------------------|-------|
| SpeechTranscriber                 | 18.8% |
| SpeechTranscriber + vocabulary    | 18.8% |
| DictationTranscriber              | 25.9% |
| DictationTranscriber + vocabulary | 17.6% |

`SpeechTranscriber` has the better acoustic model but **ignores**
`AnalysisContext.contextualStrings` — output is byte-identical with and without
terms. `DictationTranscriber` is weaker bare yet consumes them, and biasing
matters more than the model on jargon, so it is the default here. Add repair
rules on top and it reaches 12.9%, the best measured configuration.

Both avoid the session limit that forces the transcript stitching in
`apple_stt.py`: 40 of 40 sentences recovered from 83 seconds of audio, with no
reassembly.

The subprocess costs a few tens of milliseconds per utterance. Against a
recogniser that runs far faster than real time, that is a fair trade.
"""

import asyncio
import json
import os
import subprocess
import sys
import tempfile
from collections.abc import AsyncGenerator
from pathlib import Path

from loguru import logger

from pipecat.frames.frames import ErrorFrame, Frame, TranscriptionFrame
from pipecat.services.settings import STTSettings
from pipecat.services.stt_service import SegmentedSTTService
from pipecat.transcriptions.language import Language
from pipecat.utils.time import time_now_iso8601

def get_helper_path(binary_name: str) -> Path:
    if getattr(sys, "frozen", False) and hasattr(sys, "_MEIPASS"):
        p1 = Path(sys._MEIPASS) / binary_name
        if p1.exists():
            return p1
        p2 = Path(sys._MEIPASS) / "swift" / binary_name
        if p2.exists():
            return p2
    if getattr(sys, "frozen", False):
        res_dir = Path(sys.executable).parent.parent / "Resources"
        p1 = res_dir / binary_name
        if p1.exists():
            return p1
        p2 = res_dir / "swift" / binary_name
        if p2.exists():
            return p2
    return Path(__file__).parent / "swift" / binary_name

HELPER = get_helper_path("speech-helper")

# Generous: the helper may be downloading the on-device model on first use.
_FIRST_RUN_TIMEOUT = 300.0
_TIMEOUT_BASE = 15.0
_TIMEOUT_PER_AUDIO_SECOND = 0.5

# A locally built binary that has not been through this Mac's approval process
# is SIGKILLed on launch rather than failing in any legible way.
_KILLED = -9


def _needs_approval(returncode: int) -> bool:
    return returncode in (_KILLED, 137)


async def _run_helper(args: list[str], timeout: float) -> tuple[int, str, str]:
    process = await asyncio.create_subprocess_exec(
        str(HELPER),
        *args,
        stdout=asyncio.subprocess.PIPE,
        stderr=asyncio.subprocess.PIPE,
    )
    try:
        stdout, stderr = await asyncio.wait_for(process.communicate(), timeout)
    except asyncio.TimeoutError:
        process.kill()
        raise
    return process.returncode, stdout.decode(errors="replace"), stderr.decode(errors="replace")


def probe(locale: str = "en-US") -> tuple[bool, str]:
    """Check whether the helper exists, is allowed to run, and has its model.

    Blocking on purpose: this runs while the pipeline is being assembled, which
    may already be inside an event loop, so it cannot start one of its own.
    """
    if not HELPER.exists():
        return False, f"helper not built — run {HELPER.parent}/build.sh"

    try:
        result = subprocess.run(
            [str(HELPER), "--check", "--locale", locale],
            capture_output=True,
            text=True,
            timeout=_FIRST_RUN_TIMEOUT,
        )
    except subprocess.TimeoutExpired:
        return False, "helper timed out during its availability check"
    except OSError as e:
        return False, str(e)
    returncode, stdout, stderr = result.returncode, result.stdout, result.stderr

    if _needs_approval(returncode):
        return False, (
            "the helper was killed on launch, which on this managed Mac means the "
            f"binary is still awaiting approval. Request approval for {HELPER}, "
            "then try again."
        )
    if returncode != 0:
        return False, (stderr.strip() or stdout.strip() or f"helper exited {returncode}")

    try:
        payload = json.loads(stdout)
    except json.JSONDecodeError:
        return False, f"unreadable helper output: {stdout[:120]!r}"
    if not payload.get("available"):
        return False, f"no SpeechTranscriber model for {locale}"
    return True, f"SpeechAnalyzer ready, assets {payload.get('assets', 'unknown')}"


class SpeechAnalyzerSTTService(SegmentedSTTService):
    """Transcribe VAD-delimited segments with SpeechTranscriber."""

    def __init__(
        self,
        *,
        locale: str = "en-US",
        language: Language = Language.EN_US,
        vocabulary=None,
        want_alternatives: bool = False,
        module: str = "dictation",
        **kwargs,
    ):
        super().__init__(settings=STTSettings(model=None, language=locale), **kwargs)
        self._locale = locale
        self._language = language
        self._vocabulary = vocabulary
        self._want_alternatives = want_alternatives
        # "dictation" consumes the vocabulary; "transcriber" has the stronger
        # acoustic model but ignores it. See the module docstring.
        self._module = module

    def can_generate_metrics(self) -> bool:
        return True

    async def run_stt(self, audio: bytes) -> AsyncGenerator[Frame, None]:
        """Transcribe one speech segment.

        Args:
            audio: The segment as a WAV container, per ``wants_wav_segments``.
        """
        await self.start_processing_metrics()
        with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as f:
            f.write(audio)
            path = f.name

        audio_seconds = max(0.0, (len(audio) - 44) / 2 / self.sample_rate)
        args = [path, "--locale", self._locale]
        if self._vocabulary and (terms := self._vocabulary.terms()):
            args += ["--terms", ",".join(terms)]
        if self._want_alternatives:
            args.append("--alternatives")
        if self._module == "dictation":
            args.append("--dictation")

        try:
            returncode, stdout, stderr = await _run_helper(
                args, _TIMEOUT_BASE + _TIMEOUT_PER_AUDIO_SECOND * audio_seconds
            )
        except asyncio.TimeoutError:
            await self.stop_processing_metrics()
            yield ErrorFrame(error="SpeechAnalyzer helper timed out")
            return
        except Exception as e:
            await self.stop_processing_metrics()
            yield ErrorFrame(error=f"SpeechAnalyzer helper failed: {e}")
            return
        finally:
            os.unlink(path)

        await self.stop_processing_metrics()

        if returncode != 0:
            detail = stderr.strip() or stdout.strip() or f"exited {returncode}"
            yield ErrorFrame(error=f"SpeechAnalyzer helper failed: {detail}")
            return

        try:
            payload = json.loads(stdout)
        except json.JSONDecodeError:
            yield ErrorFrame(error=f"unreadable helper output: {stdout[:120]!r}")
            return
        if "error" in payload:
            yield ErrorFrame(error=f"SpeechAnalyzer: {payload['error']}")
            return

        text = (payload.get("text") or "").strip()
        if not text:
            return

        logger.debug(f"Transcription: [{text}]")
        yield TranscriptionFrame(text, self._user_id, time_now_iso8601(), self._language)