stackvox 0.2.0__py3-none-any.whl

stackvox/__init__.py

@@ -0,0 +1,16 @@
+"""stackvox — offline TTS using Kokoro-82M."""
+
+from importlib.metadata import PackageNotFoundError
+from importlib.metadata import version as _pkg_version
+
+from stackvox import daemon
+from stackvox.engine import Stackvox, speak, synthesize
+
+try:
+    __version__ = _pkg_version("stackvox")
+except PackageNotFoundError:
+    # Running from a source tree without the package installed (e.g. editable
+    # bootstrap before `pip install -e .` has completed).
+    __version__ = "0.0.0+unknown"
+
+__all__ = ["Stackvox", "daemon", "speak", "synthesize"]

stackvox/__main__.py

@@ -0,0 +1,10 @@
+"""Entry point for `python -m stackvox`."""
+
+from __future__ import annotations
+
+import sys
+
+from stackvox.cli import main
+
+if __name__ == "__main__":
+    sys.exit(main())

stackvox/cli.py

@@ -0,0 +1,179 @@
+"""CLI: `stackvox <subcommand>` or `stackvox "text"` (defaults to speak)."""
+
+from __future__ import annotations
+
+import argparse
+import logging
+import sys
+from pathlib import Path
+
+import soundfile as sf
+
+from stackvox import daemon
+from stackvox.engine import DEFAULT_LANG, DEFAULT_SPEED, DEFAULT_VOICE, Stackvox
+
+
+def _configure_logging() -> None:
+    logging.basicConfig(
+        level=logging.INFO,
+        format="[stackvox] %(message)s",
+        stream=sys.stderr,
+    )
+
+
+SUBCOMMANDS = {"serve", "stop", "status", "say", "speak", "voices", "welcome"}
+
+WELCOME_LINES = [
+    ("bf_emma", "en-gb", "Welcome to stackvox."),
+    ("af_heart", "en-us", "Welcome to stackvox."),
+    ("ff_siwis", "fr-fr", "Bienvenue sur stackvox."),
+    ("hf_alpha", "hi", "Stackvox mein aapka swagat hai."),
+    ("if_sara", "it", "Benvenuti a stackvox."),
+    ("pf_dora", "pt-br", "Bem-vindo ao stackvox."),
+]
+
+
+def _build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(prog="stackvox", description="Kokoro-82M TTS")
+    sub = parser.add_subparsers(dest="cmd")
+
+    p_speak = sub.add_parser("speak", help="Synthesize and play in-process (loads model each run)")
+    _add_voice_args(p_speak)
+    p_speak.add_argument("text", nargs="?")
+    p_speak.add_argument("--file", type=Path)
+    p_speak.add_argument("--out", type=Path, help="Write wav instead of playing")
+
+    p_say = sub.add_parser("say", help="Send text to daemon (fast; fails if daemon not running)")
+    _add_voice_args(p_say)
+    p_say.add_argument("text", nargs="?")
+    p_say.add_argument("--file", type=Path)
+    p_say.add_argument(
+        "--fallback-say", action="store_true", help="Shell out to macOS `say` if daemon unreachable"
+    )
+
+    p_serve = sub.add_parser("serve", help="Run the daemon in the foreground")
+    _add_voice_args(p_serve)
+
+    sub.add_parser("stop", help="Stop the running daemon")
+    sub.add_parser("status", help="Print daemon status")
+    sub.add_parser("voices", help="List available voices")
+    sub.add_parser("welcome", help="Play a multilingual welcome message")
+
+    return parser
+
+
+def _add_voice_args(parser: argparse.ArgumentParser) -> None:
+    parser.add_argument("--voice", default=DEFAULT_VOICE)
+    parser.add_argument("--speed", type=float, default=DEFAULT_SPEED)
+    parser.add_argument("--lang", default=DEFAULT_LANG)
+
+
+def _read_text(args: argparse.Namespace) -> str | None:
+    file: Path | None = getattr(args, "file", None)
+    if file is not None:
+        return file.read_text(encoding="utf-8")
+    text: str | None = getattr(args, "text", None)
+    return text
+
+
+def _cmd_speak(args: argparse.Namespace) -> int:
+    text = _read_text(args)
+    if not text or not text.strip():
+        print("Error: provide text or --file", file=sys.stderr)
+        return 1
+    tts = Stackvox(voice=args.voice, speed=args.speed, lang=args.lang)
+    if args.out:
+        samples, sr = tts.synthesize(text)
+        sf.write(args.out, samples, sr)
+        print(f"Wrote {args.out}", file=sys.stderr)
+    else:
+        tts.speak(text)
+    return 0
+
+
+def _cmd_say(args: argparse.Namespace) -> int:
+    text = _read_text(args)
+    if not text or not text.strip():
+        print("Error: provide text or --file", file=sys.stderr)
+        return 1
+    ok, resp = daemon.say(text, voice=args.voice, speed=args.speed, lang=args.lang)
+    if ok:
+        return 0
+    if args.fallback_say:
+        import shutil
+        import subprocess
+
+        if shutil.which("say"):
+            subprocess.run(["say", text], check=False)
+            return 0
+    print(f"[stackvox] {resp}", file=sys.stderr)
+    return 2
+
+
+def _cmd_serve(args: argparse.Namespace) -> int:
+    try:
+        daemon.serve(voice=args.voice, speed=args.speed, lang=args.lang)
+    except RuntimeError as exc:
+        print(f"[stackvox] {exc}", file=sys.stderr)
+        return 1
+    return 0
+
+
+def _cmd_stop(_: argparse.Namespace) -> int:
+    if not daemon.is_running():
+        print("[stackvox] daemon not running", file=sys.stderr)
+        return 0
+    ok, resp = daemon.stop()
+    print(resp, file=sys.stderr)
+    return 0 if ok else 1
+
+
+def _cmd_status(_: argparse.Namespace) -> int:
+    if daemon.is_running():
+        print(f"running (pid {daemon.PID_PATH.read_text().strip()}) on {daemon.SOCKET_PATH}")
+        return 0
+    print("stopped")
+    return 1
+
+
+def _cmd_voices(args: argparse.Namespace) -> int:
+    tts = Stackvox()
+    for name in tts.voices():
+        print(name)
+    return 0
+
+
+def _cmd_welcome(_: argparse.Namespace) -> int:
+    tts = Stackvox()
+    tts.speak_sequence([{"text": text, "voice": voice, "lang": lang} for voice, lang, text in WELCOME_LINES])
+    return 0
+
+
+def main() -> int:
+    _configure_logging()
+    argv = sys.argv[1:]
+    # Back-compat: `stackvox "text"` with no subcommand → speak.
+    if argv and argv[0] not in SUBCOMMANDS and not argv[0].startswith("-"):
+        argv = ["speak", *argv]
+
+    parser = _build_parser()
+    args = parser.parse_args(argv)
+
+    if not args.cmd:
+        parser.print_help()
+        return 1
+
+    handlers = {
+        "speak": _cmd_speak,
+        "say": _cmd_say,
+        "serve": _cmd_serve,
+        "stop": _cmd_stop,
+        "status": _cmd_status,
+        "voices": _cmd_voices,
+        "welcome": _cmd_welcome,
+    }
+    return handlers[args.cmd](args)
+
+
+if __name__ == "__main__":
+    sys.exit(main())

stackvox/daemon.py

@@ -0,0 +1,214 @@
+"""Long-running daemon that preloads Kokoro and plays speech on request.
+
+Avoids the ~1-2s model load on every invocation. Listens on a unix socket.
+Protocol: one JSON object per connection (line-terminated), reply is a status line.
+
+Request shapes:
+    {"text": "...", "voice": "af_sarah", "speed": 1.0, "lang": "en-us"}
+    {"command": "stop"}
+    {"command": "ping"}
+
+Replies: "ok", "busy", "err: <msg>".
+"""
+
+from __future__ import annotations
+
+import json
+import logging
+import os
+import queue
+import signal
+import socket
+import socketserver
+import threading
+
+import sounddevice as sd
+
+from stackvox.engine import DEFAULT_LANG, DEFAULT_SPEED, DEFAULT_VOICE, Stackvox
+from stackvox.paths import pid_path, socket_path
+
+logger = logging.getLogger(__name__)
+
+SOCKET_PATH = socket_path()
+PID_PATH = pid_path()
+MAX_QUEUE = 2
+WORKER_POLL_SECONDS = 0.5
+CLIENT_TIMEOUT_SECONDS = 1.0
+PING_TIMEOUT_SECONDS = 0.5
+RECV_BYTES = 1024
+
+
+def _refresh_audio_devices() -> None:
+    """Reset PortAudio so the next play picks up the current system default.
+
+    PortAudio caches the default output device at init time; without this the
+    daemon keeps playing to whatever was default when it started (e.g. the
+    built-in speakers after the user swapped to Bluetooth). Terminating and
+    re-initialising is the only portable way to refresh that cache. Costs
+    ~10-50ms per call, which is invisible next to synthesis time.
+    """
+    try:
+        sd._terminate()
+        sd._initialize()
+    except Exception:
+        logger.exception("failed to refresh audio devices")
+
+
+class _DaemonState:
+    def __init__(self, voice: str, speed: float, lang: str) -> None:
+        self.tts = Stackvox(voice=voice, speed=speed, lang=lang)
+        self.queue: queue.Queue[dict] = queue.Queue(maxsize=MAX_QUEUE)
+        self.stop_event = threading.Event()
+        self.worker = threading.Thread(target=self._worker, daemon=True)
+        self.worker.start()
+
+    def _worker(self) -> None:
+        while not self.stop_event.is_set():
+            try:
+                req = self.queue.get(timeout=WORKER_POLL_SECONDS)
+            except queue.Empty:
+                continue
+            _refresh_audio_devices()
+            try:
+                self.tts.speak(
+                    req["text"],
+                    voice=req.get("voice"),
+                    speed=req.get("speed"),
+                    lang=req.get("lang"),
+                )
+            except Exception:
+                logger.exception("playback error")
+
+    def submit(self, req: dict) -> bool:
+        try:
+            self.queue.put_nowait(req)
+            return True
+        except queue.Full:
+            return False
+
+    def shutdown(self) -> None:
+        self.stop_event.set()
+
+
+class _Handler(socketserver.StreamRequestHandler):
+    def handle(self) -> None:
+        line = self.rfile.readline().decode("utf-8", errors="replace").strip()
+        if not line:
+            return
+
+        try:
+            req = json.loads(line)
+        except json.JSONDecodeError:
+            req = {"text": line}
+
+        state: _DaemonState = self.server.state  # type: ignore[attr-defined]
+        command = req.get("command")
+
+        if command == "ping":
+            self.wfile.write(b"ok\n")
+            return
+
+        if command == "stop":
+            self.wfile.write(b"ok\n")
+            threading.Thread(target=self.server.shutdown, daemon=True).start()
+            return
+
+        text = req.get("text")
+        if not text:
+            self.wfile.write(b"err: missing text\n")
+            return
+
+        if state.submit(req):
+            self.wfile.write(b"ok\n")
+        else:
+            self.wfile.write(b"busy\n")
+
+
+class _UnixServer(socketserver.ThreadingMixIn, socketserver.UnixStreamServer):
+    allow_reuse_address = True
+    daemon_threads = True
+
+
+def _pid_alive(pid: int) -> bool:
+    try:
+        os.kill(pid, 0)
+        return True
+    except OSError:
+        return False
+
+
+def is_running() -> bool:
+    if not PID_PATH.exists():
+        return False
+    try:
+        pid = int(PID_PATH.read_text().strip())
+    except ValueError:
+        return False
+    return _pid_alive(pid)
+
+
+def serve(voice: str = DEFAULT_VOICE, speed: float = DEFAULT_SPEED, lang: str = DEFAULT_LANG) -> None:
+    if is_running():
+        raise RuntimeError(f"daemon already running (pid {PID_PATH.read_text().strip()})")
+
+    SOCKET_PATH.parent.mkdir(parents=True, exist_ok=True)
+    if SOCKET_PATH.exists():
+        SOCKET_PATH.unlink()
+
+    state = _DaemonState(voice=voice, speed=speed, lang=lang)
+    server = _UnixServer(str(SOCKET_PATH), _Handler)
+    server.state = state  # type: ignore[attr-defined]
+
+    PID_PATH.write_text(str(os.getpid()))
+
+    def handle_signal(signum: int, frame: object) -> None:
+        state.shutdown()
+        threading.Thread(target=server.shutdown, daemon=True).start()
+
+    signal.signal(signal.SIGTERM, handle_signal)
+    signal.signal(signal.SIGINT, handle_signal)
+
+    logger.info("daemon listening on %s (pid %d)", SOCKET_PATH, os.getpid())
+    try:
+        server.serve_forever()
+    finally:
+        SOCKET_PATH.unlink(missing_ok=True)
+        PID_PATH.unlink(missing_ok=True)
+
+
+def send(req: dict, timeout: float = CLIENT_TIMEOUT_SECONDS) -> tuple[bool, str]:
+    """Send a request to the daemon. Returns (ok, response)."""
+    if not SOCKET_PATH.exists():
+        return False, "daemon not running"
+    sock = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
+    sock.settimeout(timeout)
+    try:
+        sock.connect(str(SOCKET_PATH))
+        sock.sendall((json.dumps(req) + "\n").encode("utf-8"))
+        resp = sock.recv(RECV_BYTES).decode("utf-8", errors="replace").strip()
+        return resp == "ok", resp
+    except (TimeoutError, ConnectionRefusedError, FileNotFoundError, OSError) as exc:
+        return False, f"{type(exc).__name__}: {exc}"
+    finally:
+        sock.close()
+
+
+def say(
+    text: str, voice: str | None = None, speed: float | None = None, lang: str | None = None
+) -> tuple[bool, str]:
+    req: dict = {"text": text}
+    if voice is not None:
+        req["voice"] = voice
+    if speed is not None:
+        req["speed"] = speed
+    if lang is not None:
+        req["lang"] = lang
+    return send(req)
+
+
+def stop() -> tuple[bool, str]:
+    return send({"command": "stop"})
+
+
+def ping() -> tuple[bool, str]:
+    return send({"command": "ping"}, timeout=PING_TIMEOUT_SECONDS)

stackvox/engine.py

@@ -0,0 +1,164 @@
+"""Core engine: model loading, synthesis, and playback."""
+
+from __future__ import annotations
+
+import logging
+import urllib.request
+from pathlib import Path
+
+import numpy as np
+import sounddevice as sd
+from kokoro_onnx import Kokoro
+
+from stackvox.paths import cache_dir as _default_cache_dir
+
+logger = logging.getLogger(__name__)
+
+DEFAULT_VOICE = "af_sarah"
+DEFAULT_SPEED = 1.0
+DEFAULT_LANG = "en-us"
+
+_MODEL_URL = "https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files-v1.0/kokoro-v1.0.onnx"
+_VOICES_URL = "https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files-v1.0/voices-v1.0.bin"
+
+
+def _ensure_models(cache_dir: Path) -> tuple[Path, Path]:
+    cache_dir.mkdir(parents=True, exist_ok=True)
+    model_path = cache_dir / "kokoro-v1.0.onnx"
+    voices_path = cache_dir / "voices-v1.0.bin"
+    for path, url in [(model_path, _MODEL_URL), (voices_path, _VOICES_URL)]:
+        if path.exists():
+            continue
+        logger.info("downloading %s...", path.name)
+        urllib.request.urlretrieve(url, path)
+    return model_path, voices_path
+
+
+class Stackvox:
+    """Reusable TTS engine. Load the model once, speak many times.
+
+    Example:
+        tts = Stackvox(voice="af_bella")
+        tts.speak("Hello world")
+    """
+
+    def __init__(
+        self,
+        voice: str = DEFAULT_VOICE,
+        speed: float = DEFAULT_SPEED,
+        lang: str = DEFAULT_LANG,
+        cache_dir: Path | None = None,
+    ) -> None:
+        self.voice = voice
+        self.speed = speed
+        self.lang = lang
+        model_path, voices_path = _ensure_models(cache_dir or _default_cache_dir())
+        self._kokoro = Kokoro(str(model_path), str(voices_path))
+
+    def synthesize(
+        self,
+        text: str,
+        voice: str | None = None,
+        speed: float | None = None,
+        lang: str | None = None,
+    ) -> tuple[np.ndarray, int]:
+        """Return (samples, sample_rate) without playing."""
+        samples, sample_rate = self._kokoro.create(
+            text,
+            voice=voice or self.voice,
+            speed=speed if speed is not None else self.speed,
+            lang=lang or self.lang,
+        )
+        return samples, sample_rate
+
+    def speak(
+        self,
+        text: str,
+        voice: str | None = None,
+        speed: float | None = None,
+        lang: str | None = None,
+        blocking: bool = True,
+    ) -> None:
+        """Synthesize and play through the system default output device."""
+        samples, sample_rate = self.synthesize(text, voice=voice, speed=speed, lang=lang)
+        sd.play(samples, sample_rate)
+        if blocking:
+            sd.wait()
+
+    def stop(self) -> None:
+        """Stop any in-progress playback started with blocking=False."""
+        sd.stop()
+
+    def voices(self) -> list[str]:
+        return sorted(self._kokoro.get_voices())
+
+    def speak_sequence(
+        self,
+        lines: list[dict],
+        gap_seconds: float = 0.0,
+        concurrent: bool = True,
+    ) -> None:
+        """Synthesize multiple lines, concatenate, play as one gapless buffer.
+
+        Each line is a dict: {"text": str, "voice": str?, "speed": float?, "lang": str?}.
+        With concurrent=True, synthesis happens in parallel threads (ONNX runtime
+        releases the GIL) so the upfront wait is closer to the longest single
+        synthesis rather than the sum of all of them.
+        """
+        if not lines:
+            return
+
+        def synth(line: dict) -> tuple[np.ndarray, int]:
+            kwargs = {k: v for k, v in line.items() if k != "text"}
+            return self.synthesize(line["text"], **kwargs)
+
+        if concurrent and len(lines) > 1:
+            from concurrent.futures import ThreadPoolExecutor
+
+            with ThreadPoolExecutor(max_workers=len(lines)) as pool:
+                results = list(pool.map(synth, lines))
+        else:
+            results = [synth(line) for line in lines]
+
+        sample_rate = results[0][1]
+        segments: list[np.ndarray] = []
+        gap = np.zeros(int(sample_rate * gap_seconds), dtype=results[0][0].dtype) if gap_seconds > 0 else None
+        for idx, (samples, _) in enumerate(results):
+            segments.append(samples)
+            if gap is not None and idx < len(results) - 1:
+                segments.append(gap)
+
+        audio = np.concatenate(segments)
+        sd.play(audio, sample_rate)
+        sd.wait()
+
+
+_default: Stackvox | None = None
+
+
+def _get_default() -> Stackvox:
+    global _default
+    if _default is None:
+        _default = Stackvox()
+    return _default
+
+
+def speak(
+    text: str,
+    voice: str = DEFAULT_VOICE,
+    speed: float = DEFAULT_SPEED,
+    lang: str = DEFAULT_LANG,
+    blocking: bool = True,
+) -> None:
+    """One-shot: synthesize and play. Reuses a module-level engine across calls."""
+    _get_default().speak(text, voice=voice, speed=speed, lang=lang, blocking=blocking)
+
+
+def synthesize(
+    text: str,
+    voice: str = DEFAULT_VOICE,
+    speed: float = DEFAULT_SPEED,
+    lang: str = DEFAULT_LANG,
+) -> tuple[np.ndarray, int]:
+    """One-shot synthesis. Returns (samples, sample_rate)."""
+    return _get_default().synthesize(text, voice=voice, speed=speed, lang=lang)

stackvox/paths.py

@@ -0,0 +1,36 @@
+"""Filesystem paths used across stackvox: model cache, daemon socket, pid file.
+
+Centralising these avoids leaking private helpers between modules and keeps
+the `STACKVOX_CACHE_DIR` / `STACKVOX_SOCKET` override rules in one place.
+"""
+
+from __future__ import annotations
+
+import os
+from pathlib import Path
+
+
+def cache_dir() -> Path:
+    """Directory holding the model, voice pack, socket, and pid file.
+
+    Honours `STACKVOX_CACHE_DIR`; defaults to `~/.cache/stackvox`.
+    """
+    override = os.environ.get("STACKVOX_CACHE_DIR")
+    if override:
+        return Path(override).expanduser()
+    return Path.home() / ".cache" / "stackvox"
+
+
+def socket_path() -> Path:
+    """Unix socket the daemon listens on. Lives under `cache_dir()`.
+
+    Note: the bash `stackvox-say` helper honours `STACKVOX_SOCKET` so users
+    can point it at a socket on a different machine / mount — the Python
+    daemon does not, since it owns the socket and derives it from its own
+    cache dir.
+    """
+    return cache_dir() / "daemon.sock"
+
+
+def pid_path() -> Path:
+    return cache_dir() / "daemon.pid"

stackvox-0.2.0.data/scripts/stackvox-say

@@ -0,0 +1,67 @@
+#!/bin/bash
+# stackvox-say — fast TTS client for hooks.
+# Talks directly to the stackvox daemon over its unix socket, bypassing
+# Python startup. Falls back to macOS `say` with --fallback-say.
+#
+# Usage:
+#   stackvox-say "text"
+#   stackvox-say --voice bf_emma --speed 1.1 "text"
+#   stackvox-say --fallback-say "text"
+#   stackvox-say --socket /tmp/other.sock "text"
+#
+# Env:
+#   STACKVOX_SOCKET — override socket path (default: ~/.cache/stackvox/daemon.sock)
+
+set -u
+
+sock="${STACKVOX_SOCKET:-$HOME/.cache/stackvox/daemon.sock}"
+voice="" speed="" lang="" fallback=0 text=""
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --voice)        voice="$2"; shift 2 ;;
+    --speed)        speed="$2"; shift 2 ;;
+    --lang)         lang="$2";  shift 2 ;;
+    --fallback-say) fallback=1; shift ;;
+    --socket)       sock="$2";  shift 2 ;;
+    -h|--help)
+      sed -n '3,13p' "$0" | sed 's/^# \{0,1\}//'
+      exit 0 ;;
+    --)             shift; text="$*"; break ;;
+    -*)             echo "stackvox-say: unknown flag: $1" >&2; exit 1 ;;
+    *)              text="${text:+$text }$1"; shift ;;
+  esac
+done
+
+if [[ -z "$text" ]]; then
+  echo "stackvox-say: no text provided" >&2
+  exit 1
+fi
+
+do_fallback() {
+  if [[ $fallback -eq 1 ]] && command -v say >/dev/null; then
+    say "$text"
+    exit 0
+  fi
+  exit 2
+}
+
+[[ -S "$sock" ]]          || do_fallback
+command -v nc >/dev/null  || do_fallback
+
+# Minimal JSON escape: backslash, double quote, newline, tab.
+esc=${text//\\/\\\\}
+esc=${esc//\"/\\\"}
+esc=${esc//$'\n'/\\n}
+esc=${esc//$'\t'/\\t}
+
+payload='{"text":"'$esc'"'
+[[ -n "$voice" ]] && payload+=',"voice":"'$voice'"'
+[[ -n "$speed" ]] && payload+=',"speed":'$speed
+[[ -n "$lang"  ]] && payload+=',"lang":"'$lang'"'
+payload+='}'
+
+resp=$(printf '%s\n' "$payload" | nc -U -w 1 "$sock" 2>/dev/null)
+[[ "$resp" == "ok" ]] && exit 0
+
+do_fallback

stackvox-0.2.0.dist-info/METADATA

@@ -0,0 +1,185 @@
+Metadata-Version: 2.4
+Name: stackvox
+Version: 0.2.0
+Summary: Offline TTS library using Kokoro-82M
+Author-email: "StackOne Technologies Ltd." <engineering@stackone.com>
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/StackOneHQ/stackvox
+Project-URL: Repository, https://github.com/StackOneHQ/stackvox
+Project-URL: Issues, https://github.com/StackOneHQ/stackvox/issues
+Keywords: tts,kokoro,onnx,offline,speech
+Classifier: Operating System :: MacOS
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: kokoro-onnx>=0.4.0
+Requires-Dist: soundfile>=0.12.1
+Requires-Dist: sounddevice>=0.4.6
+Requires-Dist: numpy>=1.24
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pytest-mock>=3.12; extra == "dev"
+Requires-Dist: pytest-cov>=5.0; extra == "dev"
+Requires-Dist: ruff>=0.5; extra == "dev"
+Requires-Dist: pre-commit>=3.7; extra == "dev"
+Requires-Dist: commitizen>=3.27; extra == "dev"
+Requires-Dist: mypy>=1.11; extra == "dev"
+Dynamic: license-file
+
+# stackvox
+
+[![ci](https://github.com/StackOneHQ/stackvox/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/StackOneHQ/stackvox/actions/workflows/ci.yml)
+[![coverage](https://codecov.io/gh/StackOneHQ/stackvox/branch/main/graph/badge.svg)](https://codecov.io/gh/StackOneHQ/stackvox)
+[![python](https://img.shields.io/badge/python-3.10%2B-blue)](https://www.python.org/downloads/)
+[![license](https://img.shields.io/badge/license-Apache%202.0-blue)](./LICENSE)
+
+Offline TTS using [Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M) via [kokoro-onnx](https://github.com/thewh1teagle/kokoro-onnx). Apache 2.0 model, ~340MB, CPU real-time, plays straight to system audio. Designed to be importable as a Python library, drivable as a CLI, or poked via a unix socket for ~13ms speech requests from shell scripts.
+
+## Install
+
+Recommended — install globally with pipx so `stackvox` and `stackvox-say` end up on PATH:
+
+```bash
+pipx install git+https://github.com/StackOneHQ/stackvox.git
+```
+
+Upgrade later with `pipx install --force git+https://github.com/StackOneHQ/stackvox.git` (pipx's `upgrade` doesn't always detect new commits on git installs).
+
+Dev install from a clone:
+
+```bash
+python3 -m venv .venv && source .venv/bin/activate
+pip install -e .
+```
+
+Model + voice files auto-download to `~/.cache/stackvox/` on first use. Override with `STACKVOX_CACHE_DIR`.
+
+## CLI
+
+```bash
+stackvox "Hello world"              # synthesize and play in-process
+stackvox speak "Hi" --voice bf_emma # same, explicit subcommand
+stackvox speak "save" --out a.wav   # write wav instead of playing
+stackvox welcome                    # multilingual welcome (6 languages)
+stackvox voices                     # list all voice ids
+```
+
+Daemon mode (keeps the model resident so each subsequent call is instant):
+
+```bash
+stackvox serve         # foreground; run with `nohup stackvox serve &` to background
+stackvox status        # is the daemon up?
+stackvox say "Hello"   # send text to the daemon (fails if not running)
+stackvox stop          # graceful shutdown
+```
+
+## `stackvox-say` (bash helper, ~13ms)
+
+When you want minimum latency from shell scripts (hooks, CI steps, etc.), skip the Python client and use the bash helper — it talks directly to the daemon's unix socket via `nc`:
+
+```bash
+stackvox-say "back to you in 5"
+stackvox-say --voice bf_emma --speed 1.1 "hello"
+stackvox-say --fallback-say "text"     # shell out to macOS `say` if daemon is down
+```
+
+Exit codes: `0` ok, `2` daemon unreachable (unless `--fallback-say` was given).
+
+## Python library
+
+```python
+from stackvox import Stackvox, speak, synthesize
+
+# One-shot — model loads on first call, reused for subsequent calls.
+speak("Hello world")
+
+# Reusable engine.
+tts = Stackvox(voice="af_bella")
+tts.speak("First line")
+tts.speak("Faster", speed=1.2)
+
+# Non-blocking playback.
+tts.speak("async", blocking=False)
+tts.stop()
+
+# Raw samples for custom processing.
+samples, sr = tts.synthesize("give me the array")
+
+# Gapless multi-line playback with concurrent synthesis.
+tts.speak_sequence([
+    {"text": "Hello", "voice": "af_heart", "lang": "en-us"},
+    {"text": "Bonjour", "voice": "ff_siwis", "lang": "fr-fr"},
+])
+```
+
+### Daemon client from Python
+
+```python
+from stackvox import daemon
+
+ok, resp = daemon.say("queue this via the running daemon")
+if daemon.is_running():
+    daemon.stop()
+```
+
+## Voices
+
+Kokoro ships voices across several languages. Voice prefix encodes gender + language:
+
+| Prefix         | Language         | Example                  |
+| -------------- | ---------------- | ------------------------ |
+| `af_*`, `am_*` | American English | `af_heart`, `am_michael` |
+| `bf_*`, `bm_*` | British English  | `bf_emma`, `bm_fable`    |
+| `ff_*`         | French           | `ff_siwis`               |
+| `hf_*`, `hm_*` | Hindi            | `hf_alpha`, `hm_omega`   |
+| `if_*`, `im_*` | Italian          | `if_sara`, `im_nicola`   |
+| `pf_*`, `pm_*` | Portuguese       | `pf_dora`, `pm_alex`     |
+| `ef_*`, `em_*` | Spanish          | `ef_dora`, `em_alex`     |
+| `jf_*`, `jm_*` | Japanese         | `jf_alpha`               |
+| `zf_*`, `zm_*` | Mandarin Chinese | `zf_xiaoxiao`            |
+
+Run `stackvox voices` for the authoritative list.
+
+## Architecture
+
+```
+┌────────────────────┐      unix socket           ┌─────────────────────────┐
+│  stackvox-say      │ ───────────────────────▶   │  stackvox daemon        │
+│  (bash, ~13ms)     │   JSON line per request    │  (Python, long-lived)   │
+└────────────────────┘                            │                         │
+┌────────────────────┐      ~500ms (Py startup)   │  preloaded Kokoro ONNX  │
+│  stackvox say      │ ───────────────────────▶   │  worker thread playback │
+│  (Python client)   │                            │  → sounddevice → audio  │
+└────────────────────┘                            └─────────────────────────┘
+┌────────────────────┐
+│  stackvox speak    │   loads model in-process, plays, exits
+│  (one-shot CLI)    │
+└────────────────────┘
+```
+
+Socket lives at `~/.cache/stackvox/daemon.sock` (override with `STACKVOX_SOCKET` for the client, `STACKVOX_CACHE_DIR` for the daemon). Protocol is one line of JSON per connection: `{"text":"...", "voice":"...", "speed":1.0, "lang":"en-us"}`; reply is `ok` / `busy` / `err: <msg>`. Plain text (no JSON) is accepted as a fallback and treated as `{"text": line}`.
+
+Queue depth is 2 — rapid-fire requests beyond that get `busy` rather than piling up.
+
+Before each utterance the daemon resets PortAudio so it picks up the current system default output device. Swap from speakers to Bluetooth headphones mid-session and the next `say` follows you — no daemon restart needed. The refresh costs ~10–50ms per play, which is invisible next to synthesis time.
+
+## Requirements
+
+- Python 3.10+
+- macOS or Linux
+- `nc` (BSD netcat — default on macOS, `netcat-openbsd` on Linux) for the bash helper
+
+## License & attributions
+
+stackvox itself is licensed under the **Apache License, Version 2.0** — see [`LICENSE`](./LICENSE). Third-party attributions are collected in [`NOTICE`](./NOTICE); the summary below is informational.
+
+**Model.** Speech is generated by [Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M) (© hexgrad, Apache 2.0). The ONNX-converted weights (`kokoro-v1.0.onnx`) and voice pack (`voices-v1.0.bin`) are downloaded from the [kokoro-onnx](https://github.com/thewh1teagle/kokoro-onnx) release assets on first use and cached under `~/.cache/stackvox/`. stackvox does not modify or redistribute them.
+
+**Runtime dependencies.** [`kokoro-onnx`](https://github.com/thewh1teagle/kokoro-onnx) (MIT, © thewh1teagle), [`onnxruntime`](https://github.com/microsoft/onnxruntime) (MIT, © Microsoft), [`sounddevice`](https://python-sounddevice.readthedocs.io/) (MIT, © Matthias Geier), [`soundfile`](https://github.com/bastibe/python-soundfile) (BSD-3, © Bastian Bechtold), [`numpy`](https://numpy.org/) (BSD-3).
+
+**GPL note.** `kokoro-onnx` pulls in [`phonemizer-fork`](https://github.com/bootphon/phonemizer) as a transitive runtime dependency; it is licensed under **GPL-3.0**. stackvox does not bundle, modify, or statically link it — pip installs it alongside stackvox and the two communicate through phonemizer's published Python API at runtime. If you redistribute a combined work (e.g. a frozen binary, container image, or vendored wheel set) that includes phonemizer-fork, review GPL-3.0 obligations for that distribution.

stackvox-0.2.0.dist-info/RECORD

@@ -0,0 +1,15 @@
+stackvox/__init__.py,sha256=eAwh2UQ13cz2eyNzYwxJ50YUnfwTcjW68KXo_Yujzfk,547
+stackvox/__main__.py,sha256=YoGkms95VN4s2xp7FBahskL3qUJvkA-8ufVJsUuWBvs,172
+stackvox/cli.py,sha256=Q2ersirDvx2pt9db3M0AbuR_k7UnZYLFANOscIzSVxI,5351
+stackvox/daemon.py,sha256=QXkgeWSzCUJ9GeAuYp1uRsWeo94MYN2TemaTQKBS7gE,6384
+stackvox/engine.py,sha256=_50Tp2wbgU2bBokX_dwve-4r_45ig2xukO0B7fZvRY4,5181
+stackvox/paths.py,sha256=Kwuz3O1ThFn1Sm7UuGAPP4kn3EQdK2lB6yFCYcUcT6o,1089
+stackvox/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+stackvox-0.2.0.data/scripts/stackvox-say,sha256=d9rr0tlSJ5J5k0RzuF5jSp0h-Qx7PwBOuJoG5jwX1pA,1840
+stackvox-0.2.0.dist-info/licenses/LICENSE,sha256=CVx4HimvDfnRRN6rvesNgREDn71BcpjpX7tySJEzsWo,11309
+stackvox-0.2.0.dist-info/licenses/NOTICE,sha256=vJdZzhJ185QPNzycwOem5NApKbVU_fPhgg3PjYTW7OA,2364
+stackvox-0.2.0.dist-info/METADATA,sha256=aN7_27UjtZICP8ixdVIi957l5OgYtKSmQEKbfaihUmI,9260
+stackvox-0.2.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+stackvox-0.2.0.dist-info/entry_points.txt,sha256=B0LUAKX06oBp-dnBsIqNyCHNqfvH1Wmqz_0zxBVQJiU,47
+stackvox-0.2.0.dist-info/top_level.txt,sha256=rFjhxmtLVrms2NY2nHXkT-24JnLmHrRET5eF9CpFzyE,9
+stackvox-0.2.0.dist-info/RECORD,,

stackvox-0.2.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

stackvox-0.2.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+stackvox = stackvox.cli:main

stackvox-0.2.0.dist-info/licenses/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for describing the origin of the Work and
+      reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may accept and charge a
+      fee for accepting support, warranty, indemnity, or other liability
+      obligations and/or rights consistent with this License. However, in
+      accepting such obligations, You may act only on Your own behalf
+      and on Your sole responsibility, not on behalf of any other
+      Contributor, and only if You agree to indemnify, defend, and hold
+      each Contributor harmless for any liability incurred by, or claims
+      asserted against, such Contributor by reason of your accepting any
+      such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 StackOne Technologies Ltd.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

stackvox-0.2.0.dist-info/licenses/NOTICE

@@ -0,0 +1,62 @@
+stackvox
+Copyright 2026 StackOne Technologies Ltd.
+
+This product includes software developed by StackOne Technologies Ltd.
+(https://www.stackone.com/) and is licensed under the Apache License,
+Version 2.0. A copy of the license is provided in the LICENSE file.
+
+--------------------------------------------------------------------------------
+Third-party components
+--------------------------------------------------------------------------------
+
+This product relies on, but does not bundle, the following components. They
+are downloaded or installed separately at install / first-run time. Their
+original copyright notices and license terms apply; see the URLs below for
+the authoritative text.
+
+Kokoro-82M (TTS model weights and voice files)
+  Copyright (c) hexgrad
+  Licensed under the Apache License, Version 2.0
+  https://huggingface.co/hexgrad/Kokoro-82M
+
+  stackvox downloads the ONNX-converted model (`kokoro-v1.0.onnx`) and voice
+  pack (`voices-v1.0.bin`) from the kokoro-onnx GitHub release assets on
+  first use and caches them under `~/.cache/stackvox/`. These files are
+  neither modified nor redistributed by stackvox.
+
+kokoro-onnx
+  Copyright (c) 2025 github.com/thewh1teagle
+  Licensed under the MIT License
+  https://github.com/thewh1teagle/kokoro-onnx
+
+onnxruntime
+  Copyright (c) Microsoft Corporation
+  Licensed under the MIT License
+  https://github.com/microsoft/onnxruntime
+
+numpy
+  Copyright (c) 2005-2024, NumPy Developers
+  Licensed under the BSD 3-Clause License
+  https://numpy.org/
+
+sounddevice
+  Copyright (c) 2015-2025 Matthias Geier
+  Licensed under the MIT License
+  https://python-sounddevice.readthedocs.io/
+
+soundfile (pysoundfile)
+  Copyright (c) 2013, Bastian Bechtold
+  Licensed under the BSD 3-Clause License
+  https://github.com/bastibe/python-soundfile
+
+phonemizer-fork
+  Licensed under the GNU General Public License v3.0
+  https://github.com/bootphon/phonemizer
+
+  phonemizer-fork is a transitive runtime dependency of kokoro-onnx. It is
+  installed by pip alongside stackvox but is neither modified, bundled, nor
+  statically linked into stackvox itself — stackvox and phonemizer-fork
+  communicate only through phonemizer-fork's published Python interface at
+  runtime. Downstream users who distribute a combined work that includes
+  phonemizer-fork should review GPL-3.0 obligations for their own
+  distribution.

stackvox-0.2.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+stackvox