python-voiceio 0.3.1__tar.gz → 0.3.2__tar.gz

{python_voiceio-0.3.1/python_voiceio.egg-info → python_voiceio-0.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: python-voiceio
-Version: 0.3.1
+Version: 0.3.2
 Summary: Speak → text, locally, instantly.
 Author: Hugo Montenegro
 License-Expression: MIT
@@ -56,6 +56,7 @@ Dynamic: license-file
 [![PyPI](https://img.shields.io/pypi/v/python-voiceio)](https://pypi.org/project/python-voiceio/)
 [![Python](https://img.shields.io/pypi/pyversions/python-voiceio)](https://pypi.org/project/python-voiceio/)
 [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
+[![Downloads](https://img.shields.io/pepy/dt/python-voiceio)](https://pepy.tech/projects/python-voiceio)
 
 Speak → text, locally, instantly.
 
@@ -153,6 +154,10 @@ Press your hotkey to start recording (1s pre-buffer catches the first syllable).
 - **Works everywhere**: IBus input method for GUI apps, clipboard for terminals
 - **Wayland + X11**: evdev hotkeys work on both, no root required
 - **Pre-buffer**: never miss the first syllable
+- **Voice commands**: "new line", "comma", "scratch that", punctuation by name
+- **Autocorrect**: LLM-powered review of recurring Whisper mistakes (`voiceio correct`)
+- **Text-to-speech**: hear selected text spoken back (Piper, eSpeak, Edge TTS)
+- **Smart post-processing**: numbers ("twenty five" → "25"), punctuation, capitalization
 - **Auto-healing**: falls back to the next working backend if one fails
 - **Autostart**: optional systemd service, restarts on crash
 - **Self-diagnosing**: `voiceio doctor` checks everything, `--fix` repairs it
@@ -176,7 +181,10 @@ voiceio                  Start the daemon
 voiceio setup            Interactive setup wizard
 voiceio doctor           Health check (--fix to auto-repair)
 voiceio test             Test microphone + live transcription
+voiceio demo             Interactive guided tour of all features
 voiceio toggle           Toggle recording on a running daemon
+voiceio correct          Review and fix recurring transcription errors
+voiceio history          View transcription history
 voiceio update           Update to latest version
 voiceio service install  Autostart on login (systemd / Windows Startup)
 voiceio logs             View recent logs
@@ -250,9 +258,8 @@ Contributions welcome! See [CONTRIBUTING.md](CONTRIBUTING.md) and [open issues](
 - [ ] Multiple engine backends (whisper.cpp for Vulkan/AMD, VOSK for low-end hardware)
 - [ ] Echo cancellation (filter system audio for meeting use)
 - [ ] Wake word activation ("Hey voiceio")
-- [ ] Text-to-speech output (Piper/espeak-ng — completes the "io")
-
 **Done**
+- [x] Text-to-speech output (Piper/eSpeak/Edge TTS — completes the "io")
 - [x] LLM auto-audit dictionary (`voiceio correct --auto` — scan history with LLM, interactive correction)
 - [x] LLM post-processing via Ollama (grammar cleanup, spelling fixes on final pass)
 - [x] Corrections dictionary — auto-replace misheard words, "correct that" voice command

{python_voiceio-0.3.1 → python_voiceio-0.3.2}/README.md

@@ -4,6 +4,7 @@
 [![PyPI](https://img.shields.io/pypi/v/python-voiceio)](https://pypi.org/project/python-voiceio/)
 [![Python](https://img.shields.io/pypi/pyversions/python-voiceio)](https://pypi.org/project/python-voiceio/)
 [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
+[![Downloads](https://img.shields.io/pepy/dt/python-voiceio)](https://pepy.tech/projects/python-voiceio)
 
 Speak → text, locally, instantly.
 
@@ -101,6 +102,10 @@ Press your hotkey to start recording (1s pre-buffer catches the first syllable).
 - **Works everywhere**: IBus input method for GUI apps, clipboard for terminals
 - **Wayland + X11**: evdev hotkeys work on both, no root required
 - **Pre-buffer**: never miss the first syllable
+- **Voice commands**: "new line", "comma", "scratch that", punctuation by name
+- **Autocorrect**: LLM-powered review of recurring Whisper mistakes (`voiceio correct`)
+- **Text-to-speech**: hear selected text spoken back (Piper, eSpeak, Edge TTS)
+- **Smart post-processing**: numbers ("twenty five" → "25"), punctuation, capitalization
 - **Auto-healing**: falls back to the next working backend if one fails
 - **Autostart**: optional systemd service, restarts on crash
 - **Self-diagnosing**: `voiceio doctor` checks everything, `--fix` repairs it
@@ -124,7 +129,10 @@ voiceio                  Start the daemon
 voiceio setup            Interactive setup wizard
 voiceio doctor           Health check (--fix to auto-repair)
 voiceio test             Test microphone + live transcription
+voiceio demo             Interactive guided tour of all features
 voiceio toggle           Toggle recording on a running daemon
+voiceio correct          Review and fix recurring transcription errors
+voiceio history          View transcription history
 voiceio update           Update to latest version
 voiceio service install  Autostart on login (systemd / Windows Startup)
 voiceio logs             View recent logs
@@ -198,9 +206,8 @@ Contributions welcome! See [CONTRIBUTING.md](CONTRIBUTING.md) and [open issues](
 - [ ] Multiple engine backends (whisper.cpp for Vulkan/AMD, VOSK for low-end hardware)
 - [ ] Echo cancellation (filter system audio for meeting use)
 - [ ] Wake word activation ("Hey voiceio")
-- [ ] Text-to-speech output (Piper/espeak-ng — completes the "io")
-
 **Done**
+- [x] Text-to-speech output (Piper/eSpeak/Edge TTS — completes the "io")
 - [x] LLM auto-audit dictionary (`voiceio correct --auto` — scan history with LLM, interactive correction)
 - [x] LLM post-processing via Ollama (grammar cleanup, spelling fixes on final pass)
 - [x] Corrections dictionary — auto-replace misheard words, "correct that" voice command

{python_voiceio-0.3.1 → python_voiceio-0.3.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "python-voiceio"
-version = "0.3.1"
+version = "0.3.2"
 description = "Speak → text, locally, instantly."
 readme = "README.md"
 license = "MIT"

{python_voiceio-0.3.1 → python_voiceio-0.3.2/python_voiceio.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: python-voiceio
-Version: 0.3.1
+Version: 0.3.2
 Summary: Speak → text, locally, instantly.
 Author: Hugo Montenegro
 License-Expression: MIT
@@ -56,6 +56,7 @@ Dynamic: license-file
 [![PyPI](https://img.shields.io/pypi/v/python-voiceio)](https://pypi.org/project/python-voiceio/)
 [![Python](https://img.shields.io/pypi/pyversions/python-voiceio)](https://pypi.org/project/python-voiceio/)
 [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
+[![Downloads](https://img.shields.io/pepy/dt/python-voiceio)](https://pepy.tech/projects/python-voiceio)
 
 Speak → text, locally, instantly.
 
@@ -153,6 +154,10 @@ Press your hotkey to start recording (1s pre-buffer catches the first syllable).
 - **Works everywhere**: IBus input method for GUI apps, clipboard for terminals
 - **Wayland + X11**: evdev hotkeys work on both, no root required
 - **Pre-buffer**: never miss the first syllable
+- **Voice commands**: "new line", "comma", "scratch that", punctuation by name
+- **Autocorrect**: LLM-powered review of recurring Whisper mistakes (`voiceio correct`)
+- **Text-to-speech**: hear selected text spoken back (Piper, eSpeak, Edge TTS)
+- **Smart post-processing**: numbers ("twenty five" → "25"), punctuation, capitalization
 - **Auto-healing**: falls back to the next working backend if one fails
 - **Autostart**: optional systemd service, restarts on crash
 - **Self-diagnosing**: `voiceio doctor` checks everything, `--fix` repairs it
@@ -176,7 +181,10 @@ voiceio                  Start the daemon
 voiceio setup            Interactive setup wizard
 voiceio doctor           Health check (--fix to auto-repair)
 voiceio test             Test microphone + live transcription
+voiceio demo             Interactive guided tour of all features
 voiceio toggle           Toggle recording on a running daemon
+voiceio correct          Review and fix recurring transcription errors
+voiceio history          View transcription history
 voiceio update           Update to latest version
 voiceio service install  Autostart on login (systemd / Windows Startup)
 voiceio logs             View recent logs
@@ -250,9 +258,8 @@ Contributions welcome! See [CONTRIBUTING.md](CONTRIBUTING.md) and [open issues](
 - [ ] Multiple engine backends (whisper.cpp for Vulkan/AMD, VOSK for low-end hardware)
 - [ ] Echo cancellation (filter system audio for meeting use)
 - [ ] Wake word activation ("Hey voiceio")
-- [ ] Text-to-speech output (Piper/espeak-ng — completes the "io")
-
 **Done**
+- [x] Text-to-speech output (Piper/eSpeak/Edge TTS — completes the "io")
 - [x] LLM auto-audit dictionary (`voiceio correct --auto` — scan history with LLM, interactive correction)
 - [x] LLM post-processing via Ollama (grammar cleanup, spelling fixes on final pass)
 - [x] Corrections dictionary — auto-replace misheard words, "correct that" voice command

{python_voiceio-0.3.1 → python_voiceio-0.3.2}/tests/test_tts.py

@@ -142,7 +142,7 @@ def test_player_empty_audio():
 
 def test_tts_config_defaults():
     cfg = TTSConfig()
-    assert cfg.enabled is False
+    assert cfg.enabled is True
     assert cfg.engine == "auto"
     assert cfg.hotkey == "ctrl+alt+s"
     assert cfg.voice == ""
@@ -155,4 +155,4 @@ def test_tts_config_in_main_config():
     cfg = Config()
     assert hasattr(cfg, "tts")
     assert isinstance(cfg.tts, TTSConfig)
-    assert cfg.tts.enabled is False
+    assert cfg.tts.enabled is True

python_voiceio-0.3.2/voiceio/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.3.2"

{python_voiceio-0.3.1 → python_voiceio-0.3.2}/voiceio/config.py

@@ -105,7 +105,7 @@ class AutocorrectConfig:
 
 @dataclass
 class TTSConfig:
-    enabled: bool = False
+    enabled: bool = True
     engine: str = "auto"         # "auto" | "piper" | "espeak" | "edge-tts"
     hotkey: str = "ctrl+alt+s"   # "s" for speak
     voice: str = ""              # empty = engine default

{python_voiceio-0.3.1 → python_voiceio-0.3.2}/voiceio/numbers.py

@@ -142,6 +142,7 @@ def convert_numbers(text: str, language: str = "en") -> str:
         # Collect consecutive number words
         if _is_number_word(low) and low != "a" and low != "and":
             num_words = []
+            last_category = None  # "ones", "tens", "scale"
             j = i
             while j < len(words):
                 w = words[j].lower().rstrip(".,;:?!")
@@ -153,6 +154,7 @@ def convert_numbers(text: str, language: str = "en") -> str:
                         # "a" at start: only if followed by scale word
                         if j + 1 < len(words) and words[j + 1].lower().rstrip(".,;:?!") in _SCALES:
                             num_words.append(w)
+                            last_category = "ones"
                             j += 1
                             continue
                         break
@@ -163,7 +165,14 @@ def convert_numbers(text: str, language: str = "en") -> str:
                             j += 1
                             continue
                         break
+                    # Two consecutive ones-words = separate numbers
+                    # e.g. "one two three" should NOT become 6
+                    # But "twenty three", "one hundred", "thirteen thousand" are valid
+                    cat = "scale" if w in _SCALES else ("tens" if w in _TENS else "ones")
+                    if cat == "ones" and last_category == "ones":
+                        break
                     num_words.append(w)
+                    last_category = cat
                     j += 1
                 else:
                     break

{python_voiceio-0.3.1 → python_voiceio-0.3.2}/voiceio/service.py

@@ -57,6 +57,7 @@ Type=simple
 ExecStart={bin_path}
 Restart=on-failure
 RestartSec=3
+PassEnvironment=DISPLAY WAYLAND_DISPLAY XDG_SESSION_TYPE XDG_RUNTIME_DIR
 
 [Install]
 WantedBy=default.target

{python_voiceio-0.3.1 → python_voiceio-0.3.2}/voiceio/tts/edge_engine.py

@@ -19,12 +19,25 @@ class EdgeEngine:
     def probe(self) -> ProbeResult:
         try:
             import edge_tts  # noqa: F401
-            return ProbeResult(ok=True)
         except ImportError:
             return ProbeResult(
                 ok=False, reason="edge-tts not installed",
                 fix_hint="pip install edge-tts",
             )
+        try:
+            import soundfile  # noqa: F401
+            return ProbeResult(ok=True)
+        except ImportError:
+            pass
+        try:
+            import pydub  # noqa: F401
+            return ProbeResult(ok=True)
+        except ImportError:
+            return ProbeResult(
+                ok=False,
+                reason="edge-tts needs soundfile or pydub to decode audio",
+                fix_hint="pip install soundfile",
+            )
 
     def synthesize(self, text: str, voice: str, speed: float) -> tuple[np.ndarray, int]:
         import asyncio

{python_voiceio-0.3.1 → python_voiceio-0.3.2}/voiceio/tts/piper_engine.py

@@ -22,10 +22,11 @@ class PiperEngine:
     def probe(self) -> ProbeResult:
         try:
             import piper  # noqa: F401
+            from piper.download import ensure_voice_exists, get_voices  # noqa: F401
             return ProbeResult(ok=True)
-        except ImportError:
+        except ImportError as e:
             return ProbeResult(
-                ok=False, reason="piper-tts not installed",
+                ok=False, reason=f"piper-tts not fully installed: {e}",
                 fix_hint="pip install piper-tts",
             )