kittensynth 0.1.0__py3-none-any.whl

kittensynth/__init__.py

@@ -0,0 +1,24 @@
+"""KittenTTS synthesis frontend backed by kitteng2p + OnnxVoice."""
+
+from importlib.metadata import PackageNotFoundError
+from importlib.metadata import version as _distribution_version
+
+from .config import SynthesisConfig
+from .types import SynthesisResult, VoiceInfo
+from .voice import KittenVoice
+from .voice_bank import DEFAULT_VOICE_ALIASES, VoiceBank
+
+try:
+    __version__ = _distribution_version("kittensynth")
+except PackageNotFoundError:
+    __version__ = "0+unknown"
+
+__all__ = [
+    "__version__",
+    "DEFAULT_VOICE_ALIASES",
+    "KittenVoice",
+    "SynthesisConfig",
+    "SynthesisResult",
+    "VoiceBank",
+    "VoiceInfo",
+]

kittensynth/__main__.py

@@ -0,0 +1,33 @@
+from __future__ import annotations
+
+import argparse
+
+from .voice import KittenVoice
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description="Synthesize one prepared KittenTTS request")
+    parser.add_argument("text")
+    parser.add_argument("--model", default="nano-0.8-int8")
+    parser.add_argument("--voice", default="Jasper")
+    parser.add_argument("--speed", type=float, default=1.0)
+    parser.add_argument("-o", "--output", default="kitten.wav")
+    parser.add_argument("--cache-dir")
+    parser.add_argument("--catalog-url")
+    parser.add_argument("--offline", action="store_true")
+    args = parser.parse_args()
+
+    with KittenVoice.from_pretrained(
+        args.model,
+        cache_dir=args.cache_dir,
+        catalog_url=args.catalog_url,
+        offline=args.offline,
+    ) as model:
+        result = model.synthesize_prepared(args.text, voice=args.voice, speed=args.speed)
+        result.save_wav(args.output)
+    print(args.output)
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

kittensynth/_onnxvoice.py

@@ -0,0 +1,195 @@
+from __future__ import annotations
+
+import json
+import os
+from collections.abc import Mapping, Sequence
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Any
+
+from .errors import OnnxVoiceContractError, UnsupportedModelError
+from .voice_bank import DEFAULT_VOICE_ALIASES
+
+DEFAULT_CATALOG_URL = (
+    "https://raw.githubusercontent.com/buchwandler/kitten-onnx-bundles/main/catalog/models.json"
+)
+
+
+@dataclass(frozen=True, slots=True)
+class ResolvedKittenModel:
+    ref: str
+    model_id: str
+    model_path: Path
+    voices_path: Path
+    sample_rate: int
+    metadata: dict[str, Any]
+    installation: Any
+
+
+def _module() -> Any:
+    try:
+        import onnxvoice
+    except ModuleNotFoundError as exc:
+        raise OnnxVoiceContractError("OnnxVoice is required for Kitten synthesis") from exc
+    return onnxvoice
+
+
+def normalize_ref(value: str) -> str:
+    value = str(value).strip()
+    if not value:
+        raise ValueError("model reference cannot be empty")
+    return value if ":" in value else f"kitten:{value}"
+
+
+def _manager(
+    *,
+    cache_dir: str | Path | None,
+    offline: bool,
+    catalog_url: str | None,
+) -> Any:
+    module = _module()
+    source = catalog_url or os.getenv("KITTENSYNTH_CATALOG_URL") or DEFAULT_CATALOG_URL
+    try:
+        return module.OnnxVoice(
+            cache_dir=cache_dir,
+            catalog_sources={"kitten": source},
+            offline=offline,
+        )
+    except TypeError as exc:
+        raise OnnxVoiceContractError(
+            "Installed OnnxVoice does not expose the expected manager constructor"
+        ) from exc
+
+
+def installation_to_model(installation: Any) -> ResolvedKittenModel:
+    if str(getattr(installation, "system", "")) != "kitten":
+        raise UnsupportedModelError("expected an OnnxVoice Kitten installation")
+    try:
+        model_path = Path(installation.artifact("model").path)
+        voices_path = Path(installation.artifact("voices").path)
+    except (KeyError, AttributeError) as exc:
+        raise UnsupportedModelError(
+            "Kitten installation must contain model and voices artifacts"
+        ) from exc
+
+    metadata = dict(getattr(installation, "metadata", {}) or {})
+    metadata.setdefault("voice_aliases", dict(DEFAULT_VOICE_ALIASES))
+    metadata.setdefault("speed_priors", {})
+    sample_rate = int(
+        getattr(installation, "sample_rate", None) or metadata.get("sample_rate") or 24000
+    )
+    return ResolvedKittenModel(
+        ref=str(getattr(installation, "ref", f"kitten:{getattr(installation, 'id', 'unknown')}")),
+        model_id=str(getattr(installation, "id", "unknown")),
+        model_path=model_path,
+        voices_path=voices_path,
+        sample_rate=sample_rate,
+        metadata=metadata,
+        installation=installation,
+    )
+
+
+def install_pretrained_model(
+    ref: str,
+    *,
+    quality: str | None = None,
+    cache_dir: str | Path | None = None,
+    offline: bool = False,
+    refresh_catalog: bool = False,
+    force_download: bool = False,
+    catalog_url: str | None = None,
+    progress: Any | None = None,
+) -> ResolvedKittenModel:
+    manager = _manager(cache_dir=cache_dir, offline=offline, catalog_url=catalog_url)
+    installation = manager.install(
+        normalize_ref(ref),
+        quality=quality,
+        refresh=refresh_catalog,
+        force=force_download,
+        progress=progress,
+    )
+    return installation_to_model(installation)
+
+
+def open_installed_model(
+    resolved: ResolvedKittenModel,
+    *,
+    providers: Sequence[Any] | str | None = None,
+    provider_options: Mapping[str, Any] | None = None,
+    session_options: Any | None = None,
+    cache_dir: str | Path | None = None,
+    offline: bool = False,
+    catalog_url: str | None = None,
+) -> Any:
+    manager = _manager(cache_dir=cache_dir, offline=offline, catalog_url=catalog_url)
+    try:
+        return manager.open(
+            resolved.installation,
+            providers=providers,
+            provider_options=provider_options,
+            session_options=session_options,
+        )
+    except Exception as exc:
+        if "kitten" in str(exc).lower() or "unsupported system" in str(exc).lower():
+            raise OnnxVoiceContractError(
+                "OnnxVoice must register a 'kitten' adapter before kittensynth can infer"
+            ) from exc
+        raise
+
+
+def open_local_model(
+    *,
+    model_path: str | Path,
+    voices_path: str | Path,
+    metadata: Mapping[str, Any],
+    providers: Sequence[Any] | str | None = None,
+    provider_options: Mapping[str, Any] | None = None,
+    session_options: Any | None = None,
+) -> Any:
+    module = _module()
+    try:
+        return module.OnnxVoice.open_local(
+            system="kitten",
+            model=model_path,
+            voices=voices_path,
+            metadata=dict(metadata),
+            sample_rate=int(metadata.get("sample_rate") or 24000),
+            providers=providers,
+            provider_options=provider_options,
+            session_options=session_options,
+        )
+    except Exception as exc:
+        if "kitten" in str(exc).lower() or "unsupported system" in str(exc).lower():
+            raise OnnxVoiceContractError(
+                "OnnxVoice must register a 'kitten' adapter before local inference works"
+            ) from exc
+        raise
+
+
+def load_local_config(path: str | Path | None) -> dict[str, Any]:
+    metadata: dict[str, Any] = {
+        "sample_rate": 24000,
+        "voice_aliases": dict(DEFAULT_VOICE_ALIASES),
+        "speed_priors": {},
+        "runtime": {"profile": "ONNX2"},
+    }
+    if path is None:
+        return metadata
+
+    raw = json.loads(Path(path).read_text(encoding="utf-8"))
+    if not isinstance(raw, dict):
+        raise UnsupportedModelError("Kitten config.json must contain an object")
+    profile = raw.get("type")
+    if profile not in {"ONNX1", "ONNX2", None}:
+        raise UnsupportedModelError(f"unsupported Kitten runtime profile: {profile!r}")
+    if isinstance(raw.get("voice_aliases"), dict):
+        metadata["voice_aliases"] = {
+            str(key): str(value) for key, value in raw["voice_aliases"].items()
+        }
+    if isinstance(raw.get("speed_priors"), dict):
+        metadata["speed_priors"] = {
+            str(key): float(value) for key, value in raw["speed_priors"].items()
+        }
+    metadata["runtime"] = {"profile": profile or "ONNX2"}
+    metadata["upstream_config"] = raw
+    return metadata

kittensynth/config.py

@@ -0,0 +1,17 @@
+from __future__ import annotations
+
+import math
+from dataclasses import dataclass
+
+from .errors import InvalidSpeedError
+
+
+@dataclass(frozen=True, slots=True)
+class SynthesisConfig:
+    speed: float = 1.0
+
+    def validated(self) -> SynthesisConfig:
+        value = float(self.speed)
+        if not math.isfinite(value) or value <= 0:
+            raise InvalidSpeedError("speed must be a finite positive number")
+        return self

kittensynth/errors.py

@@ -0,0 +1,22 @@
+class KittenSynthError(Exception):
+    """Base error for kittensynth."""
+
+
+class EmptyTextError(KittenSynthError, ValueError):
+    """Raised when a synthesis request is empty."""
+
+
+class InvalidSpeedError(KittenSynthError, ValueError):
+    """Raised when speed is invalid."""
+
+
+class InvalidVoiceError(KittenSynthError, ValueError):
+    """Raised when a voice is not in the active voice archive."""
+
+
+class UnsupportedModelError(KittenSynthError, RuntimeError):
+    """Raised when an installation does not satisfy the Kitten contract."""
+
+
+class OnnxVoiceContractError(KittenSynthError, RuntimeError):
+    """Raised when the installed OnnxVoice lacks Kitten support."""

kittensynth/types.py

@@ -0,0 +1,47 @@
+from __future__ import annotations
+
+import wave
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Any
+
+import numpy as np
+
+
+@dataclass(frozen=True, slots=True)
+class VoiceInfo:
+    name: str
+    internal_id: str
+
+
+@dataclass(frozen=True, slots=True)
+class SynthesisResult:
+    audio: np.ndarray
+    sample_rate: int
+    voice: str
+    model_ref: str | None
+    speed: float
+    metadata: dict[str, Any] | None = None
+
+    def __post_init__(self) -> None:
+        audio = np.asarray(self.audio, dtype=np.float32).reshape(-1)
+        if not np.all(np.isfinite(audio)):
+            raise ValueError("audio must be finite")
+        if int(self.sample_rate) <= 0:
+            raise ValueError("sample_rate must be positive")
+        object.__setattr__(self, "audio", audio)
+        object.__setattr__(self, "sample_rate", int(self.sample_rate))
+
+    @property
+    def duration_seconds(self) -> float:
+        return float(self.audio.size) / float(self.sample_rate)
+
+    def save_wav(self, path: str | Path) -> None:
+        target = Path(path)
+        target.parent.mkdir(parents=True, exist_ok=True)
+        pcm = (np.clip(self.audio, -1.0, 1.0) * 32767.0).astype("<i2", copy=False)
+        with wave.open(str(target), "wb") as handle:
+            handle.setnchannels(1)
+            handle.setsampwidth(2)
+            handle.setframerate(self.sample_rate)
+            handle.writeframes(pcm.tobytes())

kittensynth/voice.py

@@ -0,0 +1,199 @@
+from __future__ import annotations
+
+from collections.abc import Mapping, Sequence
+from pathlib import Path
+from typing import Any
+
+import numpy as np
+from kitteng2p import KittenG2P
+
+from ._onnxvoice import (
+    install_pretrained_model,
+    load_local_config,
+    open_installed_model,
+    open_local_model,
+)
+from .config import SynthesisConfig
+from .errors import EmptyTextError
+from .types import SynthesisResult, VoiceInfo
+from .voice_bank import VoiceBank
+
+
+class KittenVoice:
+    def __init__(
+        self,
+        *,
+        runtime: Any,
+        voices_path: str | Path,
+        metadata: Mapping[str, Any],
+        model_ref: str | None,
+        g2p: KittenG2P | None = None,
+        sample_rate: int = 24000,
+    ) -> None:
+        self.runtime = runtime
+        self.model_ref = model_ref
+        self.metadata = dict(metadata)
+        self.sample_rate = int(sample_rate)
+        self._owns_g2p = g2p is None
+        self.g2p = g2p or KittenG2P()
+        self.voice_bank = VoiceBank(
+            voices_path,
+            voice_aliases=self.metadata.get("voice_aliases"),
+            speed_priors=self.metadata.get("speed_priors"),
+        )
+        self._closed = False
+
+    @classmethod
+    def from_pretrained(
+        cls,
+        model: str = "nano-0.8-int8",
+        *,
+        quality: str | None = None,
+        cache_dir: str | Path | None = None,
+        offline: bool = False,
+        refresh_catalog: bool = False,
+        force_download: bool = False,
+        catalog_url: str | None = None,
+        providers: Sequence[Any] | str | None = None,
+        provider_options: Mapping[str, Any] | None = None,
+        session_options: Any | None = None,
+        progress: Any | None = None,
+        g2p: KittenG2P | None = None,
+    ) -> KittenVoice:
+        resolved = install_pretrained_model(
+            model,
+            quality=quality,
+            cache_dir=cache_dir,
+            offline=offline,
+            refresh_catalog=refresh_catalog,
+            force_download=force_download,
+            catalog_url=catalog_url,
+            progress=progress,
+        )
+        runtime = open_installed_model(
+            resolved,
+            providers=providers,
+            provider_options=provider_options,
+            session_options=session_options,
+            cache_dir=cache_dir,
+            offline=offline,
+            catalog_url=catalog_url,
+        )
+        return cls(
+            runtime=runtime,
+            voices_path=resolved.voices_path,
+            metadata=resolved.metadata,
+            model_ref=resolved.ref,
+            g2p=g2p,
+            sample_rate=resolved.sample_rate,
+        )
+
+    @classmethod
+    def from_local(
+        cls,
+        *,
+        model_path: str | Path,
+        voices_path: str | Path,
+        config_path: str | Path | None = None,
+        providers: Sequence[Any] | str | None = None,
+        provider_options: Mapping[str, Any] | None = None,
+        session_options: Any | None = None,
+        g2p: KittenG2P | None = None,
+    ) -> KittenVoice:
+        metadata = load_local_config(config_path)
+        runtime = open_local_model(
+            model_path=model_path,
+            voices_path=voices_path,
+            metadata=metadata,
+            providers=providers,
+            provider_options=provider_options,
+            session_options=session_options,
+        )
+        return cls(
+            runtime=runtime,
+            voices_path=voices_path,
+            metadata=metadata,
+            model_ref=None,
+            g2p=g2p,
+            sample_rate=int(metadata.get("sample_rate") or 24000),
+        )
+
+    @property
+    def available_voices(self) -> tuple[str, ...]:
+        return self.voice_bank.available_voices
+
+    @property
+    def voices(self) -> tuple[VoiceInfo, ...]:
+        return tuple(
+            VoiceInfo(name=name, internal_id=self.voice_bank.resolve(name))
+            for name in self.available_voices
+        )
+
+    def synthesize_prepared(
+        self,
+        text: str,
+        *,
+        voice: str = "Jasper",
+        speed: float = 1.0,
+        config: SynthesisConfig | None = None,
+    ) -> SynthesisResult:
+        if self._closed:
+            raise RuntimeError("KittenVoice is closed")
+        if not isinstance(text, str) or not text.strip():
+            raise EmptyTextError("text must contain speakable content")
+        if config is not None:
+            speed = config.validated().speed
+
+        frontend = self.g2p.phonemize_prepared(text)
+        style = self.voice_bank.style_for(voice, text_length=len(text))
+        effective_speed = self.voice_bank.effective_speed(voice, speed)
+
+        result = self.runtime.infer(
+            frontend.token_ids,
+            style=style,
+            speed=effective_speed,
+        )
+        audio = np.asarray(result.audio, dtype=np.float32).reshape(-1)
+        sample_rate = int(getattr(result, "sample_rate", 0) or self.sample_rate)
+        return SynthesisResult(
+            audio=audio,
+            sample_rate=sample_rate,
+            voice=voice,
+            model_ref=self.model_ref,
+            speed=effective_speed,
+            metadata={
+                "phonemes": frontend.phonemes,
+                "token_count": len(frontend.token_ids),
+                "dropped_symbols": frontend.dropped_symbols,
+                "internal_voice": self.voice_bank.resolve(voice),
+            },
+        )
+
+    # Small compatibility alias for callers migrating from the first MVP.
+    synthesize_text = synthesize_prepared
+
+    def diagnostics(self) -> dict[str, object]:
+        runtime_diagnostics = getattr(self.runtime, "diagnostics", None)
+        g2p_diagnostics = getattr(getattr(self.g2p, "backend", None), "diagnostics", None)
+        return {
+            "runtime": runtime_diagnostics()
+            if callable(runtime_diagnostics)
+            else runtime_diagnostics,
+            "g2p": g2p_diagnostics,
+        }
+
+    def close(self) -> None:
+        if self._closed:
+            return
+        close = getattr(self.runtime, "close", None)
+        if callable(close):
+            close()
+        if self._owns_g2p:
+            self.g2p.close()
+        self._closed = True
+
+    def __enter__(self) -> KittenVoice:
+        return self
+
+    def __exit__(self, *_: object) -> None:
+        self.close()

kittensynth/voice_bank.py

@@ -0,0 +1,70 @@
+from __future__ import annotations
+
+import math
+from collections.abc import Mapping
+from pathlib import Path
+
+import numpy as np
+
+from .errors import InvalidSpeedError, InvalidVoiceError
+
+DEFAULT_VOICE_ALIASES: dict[str, str] = {
+    "Bella": "expr-voice-2-f",
+    "Jasper": "expr-voice-2-m",
+    "Luna": "expr-voice-3-f",
+    "Bruno": "expr-voice-3-m",
+    "Rosie": "expr-voice-4-f",
+    "Hugo": "expr-voice-4-m",
+    "Kiki": "expr-voice-5-f",
+    "Leo": "expr-voice-5-m",
+}
+
+
+class VoiceBank:
+    def __init__(
+        self,
+        path: str | Path,
+        *,
+        voice_aliases: Mapping[str, str] | None = None,
+        speed_priors: Mapping[str, float] | None = None,
+    ) -> None:
+        self.path = Path(path)
+        aliases = dict(DEFAULT_VOICE_ALIASES if voice_aliases is None else voice_aliases)
+        self.voice_aliases = {str(key): str(value) for key, value in aliases.items()}
+        self.speed_priors = {str(key): float(value) for key, value in (speed_priors or {}).items()}
+        with np.load(self.path, allow_pickle=False) as archive:
+            self._styles = {str(name): np.asarray(archive[name]) for name in archive.files}
+        if not self._styles:
+            raise ValueError("voices.npz is empty")
+
+    @property
+    def available_voices(self) -> tuple[str, ...]:
+        aliases = [
+            alias for alias, internal in self.voice_aliases.items() if internal in self._styles
+        ]
+        return tuple(aliases)
+
+    def resolve(self, voice: str) -> str:
+        internal = self.voice_aliases.get(voice, voice)
+        if internal not in self._styles:
+            choices = ", ".join(self.available_voices)
+            raise InvalidVoiceError(f"Voice {voice!r} is unavailable; choose from {choices}")
+        return internal
+
+    def style_for(self, voice: str, *, text_length: int) -> np.ndarray:
+        internal = self.resolve(voice)
+        styles = np.asarray(self._styles[internal])
+        if styles.ndim < 2 or styles.shape[0] < 1:
+            raise ValueError(f"invalid style shape for {internal}: {styles.shape}")
+        index = min(max(int(text_length), 0), styles.shape[0] - 1)
+        return np.asarray(styles[index : index + 1])
+
+    def effective_speed(self, voice: str, requested: float) -> float:
+        speed = float(requested)
+        if not math.isfinite(speed) or speed <= 0:
+            raise InvalidSpeedError("speed must be a finite positive number")
+        internal = self.resolve(voice)
+        effective = speed * self.speed_priors.get(internal, 1.0)
+        if not math.isfinite(effective) or effective <= 0:
+            raise InvalidSpeedError("effective speed must be finite and positive")
+        return effective

kittensynth-0.1.0.dist-info/METADATA

@@ -0,0 +1,189 @@
+Metadata-Version: 2.4
+Name: kittensynth
+Version: 0.1.0
+Summary: KittenTTS synthesis frontend backed by kitteng2p and OnnxVoice
+Author: kittensynth contributors
+License: Apache-2.0
+Project-URL: Repository, https://github.com/buchwandler/kittensynth
+Project-URL: Homepage, https://github.com/buchwandler/kittensynth
+Keywords: tts,kitten,kittentts,onnx,onnxruntime,speech
+Classifier: Development Status :: 3 - Alpha
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: numpy>=1.23
+Requires-Dist: kitteng2p<0.2,>=0.0
+Requires-Dist: onnxvoice<0.3,>=0.2
+Provides-Extra: cpu
+Requires-Dist: onnxvoice[cpu]<0.3,>=0.2; extra == "cpu"
+Provides-Extra: gpu
+Requires-Dist: onnxvoice[gpu]<0.3,>=0.2; extra == "gpu"
+Provides-Extra: bundled-g2p
+Requires-Dist: kitteng2p[bundled]<0.2,>=0.1; extra == "bundled-g2p"
+Provides-Extra: dev
+Requires-Dist: pytest>=8; extra == "dev"
+Requires-Dist: pytest-cov>=5; extra == "dev"
+Requires-Dist: ruff<0.17,>=0.16; extra == "dev"
+Requires-Dist: mypy>=1.11; extra == "dev"
+Requires-Dist: build>=1; extra == "dev"
+Requires-Dist: twine>=5; extra == "dev"
+Requires-Dist: packaging>=24; extra == "dev"
+Requires-Dist: tomli>=2; python_version < "3.11" and extra == "dev"
+Dynamic: license-file
+
+# kittensynth
+
+KittenTTS synthesis layer built on **kitteng2p + OnnxVoice**.
+
+This MVP follows the same repository/package shape as PiperSynth/PiperG2P:
+
+```text
+pyproject.toml
+kittensynth/
+tests/
+docs/
+```
+
+There is **no `src/` layer** and no hard-coded package version.
+
+## Architecture
+
+```text
+prepared speakable English
+        |
+        v
+kitteng2p
+  - eSpeak
+  - Kitten phoneme tokenization
+  - Kitten v0.8 token IDs
+        |
+        v
+kittensynth
+  - voice alias/style row
+  - speed-prior policy
+        |
+        v
+onnxvoice
+  - catalogs/install/cache/integrity
+  - ORT providers/sessions
+  - Kitten graph ABI
+        |
+        v
+float32 waveform
+```
+
+`kittensynth` has **no direct eSpeak or phonemizer dependency**. That is now entirely owned by
+`kitteng2p`.
+
+## Required OnnxVoice contract
+
+A future/updated OnnxVoice release must register:
+
+```text
+system = kitten
+```
+
+and expose:
+
+```python
+runtime.infer(token_ids, style=style, speed=effective_speed)
+```
+
+The installation contains at least:
+
+```text
+role=model
+role=voices
+```
+
+with 24 kHz metadata and Kitten voice aliases/speed priors.
+
+## Managed model
+
+```python
+from kittensynth import KittenVoice
+
+with KittenVoice.from_pretrained("nano-0.8-int8") as model:
+    result = model.synthesize_prepared(
+        "Hello from KittenSynth.",
+        voice="Jasper",
+    )
+    result.save_wav("hello.wav")
+```
+
+## Local model
+
+```python
+from kittensynth import KittenVoice
+
+with KittenVoice.from_local(
+    model_path="kitten_tts_nano_v0_8.onnx",
+    voices_path="voices.npz",
+    config_path="config.json",
+) as model:
+    result = model.synthesize_prepared("Local synthesis.", voice="Bella")
+    result.save_wav("local.wav")
+```
+
+## Prepared-text boundary
+
+Like PiperG2P/PiperSynth, this MVP expects prepared speakable text. Written-form semantic expansion
+(numbers, currencies, dates, URLs, abbreviations) stays outside the engine.
+
+That keeps these packages independent:
+
+```text
+semantic preparation -> kitteng2p -> kittensynth -> onnxvoice
+```
+
+## Voice selection
+
+The current v0.8 aliases are:
+
+```text
+Bella   -> expr-voice-2-f
+Jasper  -> expr-voice-2-m
+Luna    -> expr-voice-3-f
+Bruno   -> expr-voice-3-m
+Rosie   -> expr-voice-4-f
+Hugo    -> expr-voice-4-m
+Kiki    -> expr-voice-5-f
+Leo     -> expr-voice-5-m
+```
+
+The style row is selected exactly as upstream v0.8:
+
+```python
+min(len(text), style_rows - 1)
+```
+
+## Dynamic versioning
+
+Both `kitteng2p` and `kittensynth` use the same Git-tag-driven `setuptools-scm` pattern:
+
+```bash
+git tag v0.1.0
+python -m build
+```
+
+The source-ZIP fallback is `0.1.dev0`; installed `__version__` comes from distribution metadata.
+
+## Development
+
+For sibling checkout development:
+
+```bash
+python -m pip install -e ../kitteng2p
+python -m pip install -e ".[dev]"
+python -m pytest
+```
+
+Real synthesis remains blocked until OnnxVoice contains the Kitten adapter/catalog parser.

kittensynth-0.1.0.dist-info/RECORD

@@ -0,0 +1,16 @@
+kittensynth/__init__.py,sha256=6tWjOyjwEoCANVOW1wchGMk51s_74VfYSNklPP3Jj38,638
+kittensynth/__main__.py,sha256=eiWur15DGR7hUGQkT5idIEgiJxnFD9Mbsx2DxApAVmQ,1035
+kittensynth/_onnxvoice.py,sha256=23Klr4VoQL5FjVDp812E0hhoP3GcwqmKoCHFXcDKs3w,6417
+kittensynth/config.py,sha256=HFeq-bZj87-iKvp0W0bPMxpsRr21S6NZExERV3G3eCk,433
+kittensynth/errors.py,sha256=TnX3jJpcXU771snSYv8fWdk3CDI4QJz625-RgdXMndE,670
+kittensynth/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kittensynth/types.py,sha256=M-L8gx0OS3DXGuiT37_5DpL_MpkKkzJ1O-FlRP-rLH0,1426
+kittensynth/voice.py,sha256=3hTS0vfsYYeM1oC6K02nBz2EAO-0dN19S1MuDBKVo9o,6285
+kittensynth/voice_bank.py,sha256=5F_lY0SWLzaAfD9cfaJaGLGzytHpzht3E19BF2ARqG8,2694
+kittensynth-0.1.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+kittensynth-0.1.0.dist-info/licenses/NOTICE,sha256=zPSBCaahN3SRvMo60dyYJNx6zklDr02Nb_3ZNx0v8gc,210
+kittensynth-0.1.0.dist-info/METADATA,sha256=ERLp05TiPEGPgjwiT5uQGSiPHXjRltzV5ZmVxARsQNQ,4533
+kittensynth-0.1.0.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
+kittensynth-0.1.0.dist-info/entry_points.txt,sha256=yASb7Z8dBFsXLB63Xb7RNxO6LnvUzra_Qrk_k6maTx0,58
+kittensynth-0.1.0.dist-info/top_level.txt,sha256=aOF0JPP8MnfyShiLlAOaFfpdCnXayeCiYWS2RAWghMk,12
+kittensynth-0.1.0.dist-info/RECORD,,

kittensynth-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (84.0.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

kittensynth-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+kittensynth = kittensynth.__main__:main

kittensynth-0.1.0.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 reasonable and customary use in 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 choose to offer,
+      and charge a fee for, acceptance of 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 [yyyy] [name of copyright owner]
+
+   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.

kittensynth-0.1.0.dist-info/licenses/NOTICE

@@ -0,0 +1,4 @@
+kittensynth
+
+This repository contains independently authored integration/frontend code. It does not include or
+relicense KittenTTS model weights or voice-style assets. Runtime assets retain upstream licensing.

kittensynth-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+kittensynth