sonify1026 0.1.0__tar.gz

sonify1026-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 BIOS-02
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

sonify1026-0.1.0/MANIFEST.in

@@ -0,0 +1,7 @@
+include LICENSE
+include README.md
+include requirements.txt
+recursive-include snfy *.yaml
+recursive-include tests *.py
+global-exclude __pycache__/*
+global-exclude *.py[cod]

sonify1026-0.1.0/PKG-INFO

@@ -0,0 +1,198 @@
+Metadata-Version: 2.4
+Name: sonify1026
+Version: 0.1.0
+Summary: Expressive Indian female TTS voice engine with adaptive emotion, prosody and EN/HI code-switching
+Author-email: Naitik <sanjeevshrivastava898@gmail.com>
+Maintainer-email: Naitik <sanjeevshrivastava898@gmail.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/naitik0409/sonify1026
+Project-URL: Source, https://github.com/naitik0409/sonify1026
+Project-URL: Issues, https://github.com/naitik0409/sonify1026/issues
+Keywords: tts,text-to-speech,voice,speech,synthesis,hindi,hinglish,indian-english,emotion,prosody,edge-tts,text2speech
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+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
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Natural Language :: English
+Classifier: Natural Language :: Hindi
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: edge-tts>=6.1.12
+Requires-Dist: numpy>=1.26.0
+Requires-Dist: scipy>=1.11.0
+Requires-Dist: soundfile>=0.12.1
+Requires-Dist: PyYAML>=6.0.1
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: build>=1.0.0; extra == "dev"
+Requires-Dist: twine>=4.0.0; extra == "dev"
+Requires-Dist: sounddevice>=0.4.6; extra == "dev"
+Dynamic: license-file
+
+# Sonify 1026 Voice Engine
+
+[![PyPI version](https://img.shields.io/pypi/v/sonify1026.svg)](https://pypi.org/project/sonify1026/)
+[![Python](https://img.shields.io/pypi/pyversions/sonify1026.svg)](https://pypi.org/project/sonify1026/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
+
+An expressive, adaptive **Indian female TTS voice engine** — mid-20s, urban Indian
+English with native-standard Hindi code-switching.
+
+```bash
+pip install sonify1026
+```
+
+```python
+import snfy
+
+engine = snfy.SonifyEngine()
+engine.synthesize(
+    "That is wonderful news, I am so happy for you!",
+    emotion=snfy.Emotion.HAPPY,
+    output_path="out.wav",
+)
+```
+
+> Installed as **`sonify1026`**, imported as **`snfy`** — the same pattern as
+> `pip install beautifulsoup4` / `import bs4`.
+
+---
+
+## Voice profile
+
+| Aspect | Behaviour |
+|---|---|
+| Timbre | Warm, mid register with low-to-mid chest resonance; light, mid-high pitch |
+| Delivery | Spontaneous and extemporaneous — no metronomic line-reading |
+| Expressiveness | Emotional valence analysed per sentence: smiling inflection on positive phrases, acoustic softening on tender ones, subglottic lift on emphatic ones |
+| Pacing | Non-linear — pauses, rate and breathing scale with the emotional subtext |
+| Imperfections | Soft breath intakes, mouth clicks, micro-pauses, occasional vocal fry |
+| Clarity | Phase-preserving EQ, no compression, no time-stretching in the output path |
+| Uniqueness | Every call is its own performance (no fixed seed) |
+
+---
+
+## Features
+
+- **Bilingual** — English (`en-IN-NeerjaNeural`) and Hindi (`hi-IN-SwaraNeural`), with automatic Hinglish code-switching in either direction.
+- **17 emotions** — `neutral`, `happy`, `calm`, `warm`, `gentle`, `sad`, `excited`, `angry`, `fearful`, `thoughtful`, `playful`, `tired`, `proud`, `surprised`, `reassuring`, `serious`, `whisper`.
+- **Adaptive prosody** — intensity words, sentence length and emotional valence drive pitch, rate, volume, brightness, warmth, breathing interval and pause length per sentence.
+- **Emotional arc** — a script that builds in feeling sounds like it builds, instead of resetting each sentence.
+- **Register control** — `normal`, `formal`, `casual` (casual is the default).
+- **Number normalisation** — digits, decimals, times, ordinals and phone numbers are spoken naturally (both ASCII and Devanagari).
+- **Pitch guard** — verifies the rendered voice sits in the intended register and re-renders if a phrase drifts too low or high.
+- **Offline fallback** — pyttsx3 when the network is unavailable.
+- **Fully configurable** — every voice parameter lives in one YAML file; nothing is hardcoded.
+
+---
+
+## Installation
+
+```bash
+pip install sonify1026
+```
+
+Requires Python 3.9+. An internet connection is required at synthesis time
+(audio is served by Microsoft Edge TTS); no API key needed.
+
+## Usage
+
+### Python API
+
+```python
+import snfy
+
+engine = snfy.SonifyEngine()
+
+# English
+engine.synthesize("Hello! How are you today?", emotion=snfy.Emotion.WARM,
+                  output_path="en.wav")
+
+# Hindi
+engine.synthesize("नमस्ते! आपका दिन शुभ हो।", emotion=snfy.Emotion.WARM,
+                  language=snfy.Language.HI_IN, output_path="hi.wav")
+
+# Hinglish — detected automatically
+engine.synthesize("Yaar, kal ki meeting bahut important hai, on time aa jaana.",
+                  output_path="hinglish.wav")
+```
+
+Work with audio in memory:
+
+```python
+import soundfile as sf
+
+result = engine.synthesize("Hello!")      # no output_path
+sf.write("out.wav", result.audio, result.sample_rate)
+print(result.duration, result.sample_rate)  # 4.91 48000
+```
+
+### Runtime controls
+
+```python
+engine.set_speed(1.15)        # 0.5 - 2.0
+engine.set_pitch(0)           # -20 - +25 Hz
+engine.set_volume(1.0)        # 0.0 - 1.5
+engine.set_offline_mode(True) # pyttsx3 fallback
+engine.reload_config()        # re-read voice_config.yaml
+```
+
+### CLI
+
+```bash
+sonify1026 "Hello! How are you?" --emotion warm --output hello.wav
+sonify1026 "यह एक परीक्षण है।" -e calm -o test.wav
+sonify1026 "Play this." --play
+```
+
+---
+
+## Configuration
+
+All voice behaviour lives in `snfy/voice_config.yaml`. Use your own file with:
+
+```python
+engine = SonifyEngine(config_path="my_voice.yaml")
+```
+
+| Key | Effect |
+|---|---|
+| `character.base_pitch` | overall register (Hz offset) |
+| `pitch_guard` | auto-corrects register if a phrase drifts |
+| `persona.warm_hz` / `warm_gain` | chest resonance |
+| `persona.presence_gain` | high-frequency clarity |
+| `voice_settings.<voice>.eq` | per-voice tone shaping |
+| `emotions.<name>` | per-emotion rate / volume / pause / compression |
+| `dynamic_prosody.valence_words` | what counts as positive / tender / negative |
+| `breath` | breath intakes before phrases |
+| `humanize.max_utterance_chars` | where takes are split |
+
+---
+
+## Testing
+
+```bash
+pytest tests -q              # 56 objective quality/regression checks
+python tests/voice_audit.py  # full voice QA report across a corpus
+```
+
+Clarity, loudness and modulation are measured objectively from the rendered
+waveform and judged relative to the same text rendered straight through
+edge-tts, so regressions in clarity or naturalness are caught automatically.
+
+---
+
+## License
+
+MIT — see [LICENSE](LICENSE).
+
+Audio is generated by Microsoft Edge TTS; you are responsible for complying with
+its terms of use.

sonify1026-0.1.0/README.md

@@ -0,0 +1,159 @@
+# Sonify 1026 Voice Engine
+
+[![PyPI version](https://img.shields.io/pypi/v/sonify1026.svg)](https://pypi.org/project/sonify1026/)
+[![Python](https://img.shields.io/pypi/pyversions/sonify1026.svg)](https://pypi.org/project/sonify1026/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
+
+An expressive, adaptive **Indian female TTS voice engine** — mid-20s, urban Indian
+English with native-standard Hindi code-switching.
+
+```bash
+pip install sonify1026
+```
+
+```python
+import snfy
+
+engine = snfy.SonifyEngine()
+engine.synthesize(
+    "That is wonderful news, I am so happy for you!",
+    emotion=snfy.Emotion.HAPPY,
+    output_path="out.wav",
+)
+```
+
+> Installed as **`sonify1026`**, imported as **`snfy`** — the same pattern as
+> `pip install beautifulsoup4` / `import bs4`.
+
+---
+
+## Voice profile
+
+| Aspect | Behaviour |
+|---|---|
+| Timbre | Warm, mid register with low-to-mid chest resonance; light, mid-high pitch |
+| Delivery | Spontaneous and extemporaneous — no metronomic line-reading |
+| Expressiveness | Emotional valence analysed per sentence: smiling inflection on positive phrases, acoustic softening on tender ones, subglottic lift on emphatic ones |
+| Pacing | Non-linear — pauses, rate and breathing scale with the emotional subtext |
+| Imperfections | Soft breath intakes, mouth clicks, micro-pauses, occasional vocal fry |
+| Clarity | Phase-preserving EQ, no compression, no time-stretching in the output path |
+| Uniqueness | Every call is its own performance (no fixed seed) |
+
+---
+
+## Features
+
+- **Bilingual** — English (`en-IN-NeerjaNeural`) and Hindi (`hi-IN-SwaraNeural`), with automatic Hinglish code-switching in either direction.
+- **17 emotions** — `neutral`, `happy`, `calm`, `warm`, `gentle`, `sad`, `excited`, `angry`, `fearful`, `thoughtful`, `playful`, `tired`, `proud`, `surprised`, `reassuring`, `serious`, `whisper`.
+- **Adaptive prosody** — intensity words, sentence length and emotional valence drive pitch, rate, volume, brightness, warmth, breathing interval and pause length per sentence.
+- **Emotional arc** — a script that builds in feeling sounds like it builds, instead of resetting each sentence.
+- **Register control** — `normal`, `formal`, `casual` (casual is the default).
+- **Number normalisation** — digits, decimals, times, ordinals and phone numbers are spoken naturally (both ASCII and Devanagari).
+- **Pitch guard** — verifies the rendered voice sits in the intended register and re-renders if a phrase drifts too low or high.
+- **Offline fallback** — pyttsx3 when the network is unavailable.
+- **Fully configurable** — every voice parameter lives in one YAML file; nothing is hardcoded.
+
+---
+
+## Installation
+
+```bash
+pip install sonify1026
+```
+
+Requires Python 3.9+. An internet connection is required at synthesis time
+(audio is served by Microsoft Edge TTS); no API key needed.
+
+## Usage
+
+### Python API
+
+```python
+import snfy
+
+engine = snfy.SonifyEngine()
+
+# English
+engine.synthesize("Hello! How are you today?", emotion=snfy.Emotion.WARM,
+                  output_path="en.wav")
+
+# Hindi
+engine.synthesize("नमस्ते! आपका दिन शुभ हो।", emotion=snfy.Emotion.WARM,
+                  language=snfy.Language.HI_IN, output_path="hi.wav")
+
+# Hinglish — detected automatically
+engine.synthesize("Yaar, kal ki meeting bahut important hai, on time aa jaana.",
+                  output_path="hinglish.wav")
+```
+
+Work with audio in memory:
+
+```python
+import soundfile as sf
+
+result = engine.synthesize("Hello!")      # no output_path
+sf.write("out.wav", result.audio, result.sample_rate)
+print(result.duration, result.sample_rate)  # 4.91 48000
+```
+
+### Runtime controls
+
+```python
+engine.set_speed(1.15)        # 0.5 - 2.0
+engine.set_pitch(0)           # -20 - +25 Hz
+engine.set_volume(1.0)        # 0.0 - 1.5
+engine.set_offline_mode(True) # pyttsx3 fallback
+engine.reload_config()        # re-read voice_config.yaml
+```
+
+### CLI
+
+```bash
+sonify1026 "Hello! How are you?" --emotion warm --output hello.wav
+sonify1026 "यह एक परीक्षण है।" -e calm -o test.wav
+sonify1026 "Play this." --play
+```
+
+---
+
+## Configuration
+
+All voice behaviour lives in `snfy/voice_config.yaml`. Use your own file with:
+
+```python
+engine = SonifyEngine(config_path="my_voice.yaml")
+```
+
+| Key | Effect |
+|---|---|
+| `character.base_pitch` | overall register (Hz offset) |
+| `pitch_guard` | auto-corrects register if a phrase drifts |
+| `persona.warm_hz` / `warm_gain` | chest resonance |
+| `persona.presence_gain` | high-frequency clarity |
+| `voice_settings.<voice>.eq` | per-voice tone shaping |
+| `emotions.<name>` | per-emotion rate / volume / pause / compression |
+| `dynamic_prosody.valence_words` | what counts as positive / tender / negative |
+| `breath` | breath intakes before phrases |
+| `humanize.max_utterance_chars` | where takes are split |
+
+---
+
+## Testing
+
+```bash
+pytest tests -q              # 56 objective quality/regression checks
+python tests/voice_audit.py  # full voice QA report across a corpus
+```
+
+Clarity, loudness and modulation are measured objectively from the rendered
+waveform and judged relative to the same text rendered straight through
+edge-tts, so regressions in clarity or naturalness are caught automatically.
+
+---
+
+## License
+
+MIT — see [LICENSE](LICENSE).
+
+Audio is generated by Microsoft Edge TTS; you are responsible for complying with
+its terms of use.

sonify1026-0.1.0/pyproject.toml

@@ -0,0 +1,80 @@
+[build-system]
+requires = ["setuptools>=77.0.3", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "sonify1026"
+version = "0.1.0"
+description = "Expressive Indian female TTS voice engine with adaptive emotion, prosody and EN/HI code-switching"
+readme = {file = "README.md", content-type = "text/markdown"}
+requires-python = ">=3.9"
+license = "MIT"
+license-files = ["LICENSE"]
+authors = [
+    {name = "Naitik", email = "sanjeevshrivastava898@gmail.com"},
+]
+maintainers = [
+    {name = "Naitik", email = "sanjeevshrivastava898@gmail.com"},
+]
+keywords = [
+    "tts",
+    "text-to-speech",
+    "voice",
+    "speech",
+    "synthesis",
+    "hindi",
+    "hinglish",
+    "indian-english",
+    "emotion",
+    "prosody",
+    "edge-tts",
+    "text2speech",
+]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Multimedia :: Sound/Audio :: Speech",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Natural Language :: English",
+    "Natural Language :: Hindi",
+]
+dependencies = [
+    "edge-tts>=6.1.12",
+    "numpy>=1.26.0",
+    "scipy>=1.11.0",
+    "soundfile>=0.12.1",
+    "PyYAML>=6.0.1",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.0.0",
+    "build>=1.0.0",
+    "twine>=4.0.0",
+    "sounddevice>=0.4.6",
+]
+
+[project.urls]
+Homepage = "https://github.com/naitik0409/sonify1026"
+Source = "https://github.com/naitik0409/sonify1026"
+Issues = "https://github.com/naitik0409/sonify1026/issues"
+
+[project.scripts]
+sonify1026 = "snfy.__main__:main"
+snfy = "snfy.__main__:main"
+
+[tool.setuptools.packages.find]
+include = ["snfy*"]
+
+[tool.setuptools.package-data]
+snfy = ["*.yaml", "*.yml"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

sonify1026-0.1.0/requirements.txt

@@ -0,0 +1,5 @@
+edge-tts>=6.1.12
+numpy>=1.26.0
+scipy>=1.11.0
+soundfile>=0.12.1
+PyYAML>=6.0.1

sonify1026-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

sonify1026-0.1.0/snfy/__init__.py

@@ -0,0 +1,38 @@
+"""
+Sonify 1026 Voice Engine
+An expressive, adaptive Indian female TTS engine with emotion, accent,
+prosody and EN/HI code-switching control.
+"""
+
+from .engine import (
+    SonifyEngine,
+    BIOS02VoiceEngine,
+    Emotion,
+    Language,
+    Persona,
+    ProsodyParams,
+    SynthesisResult,
+    create_engine,
+    render,
+    render_arc,
+    speak,
+    REGISTERS,
+    DEFAULT_REGISTER,
+)
+
+__version__ = "0.1.0"
+__all__ = [
+    "SonifyEngine",
+    "BIOS02VoiceEngine",
+    "Emotion",
+    "Language",
+    "Persona",
+    "ProsodyParams",
+    "SynthesisResult",
+    "create_engine",
+    "render",
+    "render_arc",
+    "speak",
+    "REGISTERS",
+    "DEFAULT_REGISTER",
+]

sonify1026-0.1.0/snfy/__main__.py

@@ -0,0 +1,39 @@
+"""
+Sonify 1026 CLI - Run as: snfy "Hello world", or python -m snfy "Hello world"
+"""
+
+import argparse
+import sys
+from .engine import SonifyEngine, Emotion
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Sonify 1026 Voice Engine CLI")
+    parser.add_argument("text", help="Text to synthesize")
+    parser.add_argument("--emotion", "-e", default="neutral", help="Emotion preset")
+    parser.add_argument("--accent", "-a", default="in", choices=["in", "us"], help="Accent")
+    parser.add_argument("--output", "-o", default="output.wav", help="Output file path")
+    parser.add_argument("--play", "-p", action="store_true", help="Play audio after synthesis")
+    args = parser.parse_args()
+
+    try:
+        emotion = Emotion(args.emotion.lower())
+    except ValueError:
+        print(f"Unknown emotion: {args.emotion}. Using neutral.")
+        emotion = Emotion.NEUTRAL
+
+    engine = SonifyEngine()
+    result = engine.synthesize(args.text, emotion=emotion, accent=args.accent, output_path=args.output)
+    print(f"Saved to {args.output} ({result.duration:.2f}s)")
+
+    if args.play:
+        try:
+            import sounddevice as sd
+            sd.play(result.audio, result.sample_rate)
+            sd.wait()
+        except ImportError:
+            print("Install sounddevice to play audio: pip install sounddevice")
+
+
+if __name__ == "__main__":
+    main()