pyrospeak 0.0.1__tar.gz

pyrospeak-0.0.1/PKG-INFO

@@ -0,0 +1,73 @@
+Metadata-Version: 2.4
+Name: pyrospeak
+Version: 0.0.1
+Summary: Simple TTS & STT wrapper with multiple engines
+Author: Mureșan Robert
+License: MIT
+Project-URL: Homepage, https://github.com/Robertinoos13/PyroSpeak-Library
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: pyttsx3
+Requires-Dist: gTTS
+Requires-Dist: pygame
+Requires-Dist: numpy
+Requires-Dist: sounddevice
+Requires-Dist: whisper
+Requires-Dist: faststt
+Requires-Dist: elevenlabs
+
+# `PyroSpeak` 🗣️
+
+`PyroSpeak` is a simple and flexible Python library for Text-to-Speech (TTS) and Speech-to-Text (STT), designed to work with multiple engines, both online and offline, using a clean and beginner-friendly API.
+
+It aims to provide a single, unified interface for common speech tasks without forcing you to deal with low-level audio details.
+
+## Features
+
+- Multiple TTS engines (online & offline)
+- Multiple STT engines (FastSTT, Whisper)
+- Minimal and intuitive API
+- Suitable for experiments, bots, and small AI projects
+- Works well with real-time audio
+
+## Quick Example
+``` python
+from pyrospeak import speak, record
+
+# Text to Speech
+speak("Hello world!", engine="gtts")
+
+# Speech to Text
+text = record(engine="whisper")
+print(text)
+```
+
+## Supported Engines
+### Text-to-Speech (TTS)
+
+- gTTS (Google Text-to-Speech)
+- pyttsx3 (offline)
+- ElevenLabs (API-based)
+
+### Speech-to-Text (STT)
+
+- FastSTT
+- Whisper (OpenAI)
+
+---
+
+## Configuration
+
+Most functions are configurable through keyword arguments such as:
+- engine
+- language
+- model size / device
+- time limits
+
+Refer to the source code for full parameter lists.
+
+
+## License
+
+MIT License
+

pyrospeak-0.0.1/README.md

@@ -0,0 +1,55 @@
+# `PyroSpeak` 🗣️
+
+`PyroSpeak` is a simple and flexible Python library for Text-to-Speech (TTS) and Speech-to-Text (STT), designed to work with multiple engines, both online and offline, using a clean and beginner-friendly API.
+
+It aims to provide a single, unified interface for common speech tasks without forcing you to deal with low-level audio details.
+
+## Features
+
+- Multiple TTS engines (online & offline)
+- Multiple STT engines (FastSTT, Whisper)
+- Minimal and intuitive API
+- Suitable for experiments, bots, and small AI projects
+- Works well with real-time audio
+
+## Quick Example
+``` python
+from pyrospeak import speak, record
+
+# Text to Speech
+speak("Hello world!", engine="gtts")
+
+# Speech to Text
+text = record(engine="whisper")
+print(text)
+```
+
+## Supported Engines
+### Text-to-Speech (TTS)
+
+- gTTS (Google Text-to-Speech)
+- pyttsx3 (offline)
+- ElevenLabs (API-based)
+
+### Speech-to-Text (STT)
+
+- FastSTT
+- Whisper (OpenAI)
+
+---
+
+## Configuration
+
+Most functions are configurable through keyword arguments such as:
+- engine
+- language
+- model size / device
+- time limits
+
+Refer to the source code for full parameter lists.
+
+
+## License
+
+MIT License
+

pyrospeak-0.0.1/pyproject.toml

@@ -0,0 +1,28 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "pyrospeak"
+version = "0.0.1"
+description = "Simple TTS & STT wrapper with multiple engines"
+readme = "README.md"
+requires-python = ">=3.9"
+license = {text = "MIT"}
+authors = [
+  {name = "Mureșan Robert"}
+]
+
+dependencies = [
+  "pyttsx3",
+  "gTTS",
+  "pygame",
+  "numpy",
+  "sounddevice",
+  "whisper",
+  "faststt",
+  "elevenlabs"
+]
+
+[project.urls]
+Homepage = "https://github.com/Robertinoos13/PyroSpeak-Library"

pyrospeak-0.0.1/pyrospeak/__init__.py

@@ -0,0 +1,4 @@
+from .tts import speak
+from .stt import record
+
+__all__ = ["speak", "record"]

pyrospeak-0.0.1/pyrospeak/stt.py

@@ -0,0 +1,63 @@
+import os
+os.environ.setdefault('KMP_DUPLICATE_LIB_OK', 'TRUE')
+os.environ.setdefault('HF_HUB_DISABLE_SYMLINKS_WARNING', '1')
+
+# STT Modules
+from faststt import FastSTT
+import whisper
+
+# Other Modules
+import logging
+import sounddevice as sd
+import numpy as np
+
+def record(engine="faststt", 
+           faststt_model_size="base", 
+           faststt_device="CPU", 
+           faststt_timeout=3,
+           faststt_phrase_time_limit=5,
+           whisper_seconds=5,
+           whisper_samplerate=16000,
+           whisper_name="base",
+           whisper_device="cpu"):
+
+    # FastSTT code
+    if engine.lower() in ("faststt"):
+
+        logging.basicConfig(level=logging.INFO)
+
+        stt = FastSTT(
+            model_size=faststt_model_size.lower(), 
+            device=faststt_device.lower()
+            )
+        
+        print("Listening...")
+
+        try:
+            text = stt.listen_and_transcribe(timeout=faststt_timeout, phrase_time_limit=faststt_phrase_time_limit)
+            if text and isinstance(text, dict):
+                print("Transcription:", text["text"])
+            else:
+                print("...no speech detected")
+
+        except KeyboardInterrupt:
+            print("\nStopped by user")
+
+        except Exception as e:
+            pass
+
+        result = text
+        return result["text"] if isinstance(result, dict) else result
+    
+
+    # Whisper code
+    elif engine.lower() in ("whisper"):
+        print(f"Listening for {whisper_seconds} seconds. Speak...")
+        model = whisper.load_model(name=whisper_name.lower(), device=whisper_device.lower())
+    
+        # Înregistrare direct în memorie: float32 (formatul cerut de Whisper)
+        audio = sd.rec(int(whisper_seconds * whisper_samplerate), samplerate=whisper_samplerate, channels=1, dtype=np.float32)
+        sd.wait() # Așteaptă finalizarea înregistrării
+
+        # Transcrierea directă a array-ului aplatizat (1D)
+        return model.transcribe(audio.flatten())["text"]

pyrospeak-0.0.1/pyrospeak/tts.py

@@ -0,0 +1,83 @@
+import os
+os.environ.setdefault('KMP_DUPLICATE_LIB_OK', 'TRUE')
+os.environ.setdefault('HF_HUB_DISABLE_SYMLINKS_WARNING', '1')
+
+# TTS Modules
+import pyttsx3
+from gtts import gTTS
+from elevenlabs.client import ElevenLabs
+from elevenlabs import stream
+
+# Other
+import pygame
+import tempfile
+import os
+import sys
+import io
+
+try:
+    sys.stdout.reconfigure(encoding='utf-8')
+except Exception:
+    # Fallback pentru versiuni Python mai învechite
+    try:
+        sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8', errors='replace')
+    except Exception:
+        pass
+
+def speak(text_to_procces="", 
+          engine="gtts", 
+          language='en', 
+          elevenlabs_api_key="", 
+          elevenlabs_voice_id='21m00Tcm4TlvDq8ikWAM', 
+          elevenlabs_model_id='eleven_multilingual_v2'):
+
+    # gTTS code
+    if engine.lower() in ("gtts", 'google', 'free_online'):
+        
+        with tempfile.NamedTemporaryFile(delete=False, suffix='.mp3') as fp:
+            if language.lower() == 'auto':
+                tts = gTTS(
+                    text=text_to_procces, 
+                    lang_check=True
+                )
+
+            else:
+                tts = gTTS(
+                    text=text_to_procces,
+                    lang=language
+                )
+
+            tts.save(fp.name)
+        
+        pygame.mixer.init()
+        pygame.mixer.music.load(fp.name)
+        pygame.mixer.music.play()
+        while pygame.mixer.music.get_busy():
+            pass
+
+        pygame.mixer.music.stop()
+        pygame.mixer.quit()
+        os.unlink(fp.name)
+
+
+    # ElevenLabs code 
+    elif engine.lower() in ("elevenlabs", "pay_online", "eleven labs"):
+        
+
+        client = ElevenLabs(api_key=elevenlabs_api_key)
+
+        audio_stream = client.text_to_speech.stream(
+            text=text_to_procces,
+            voice_id=elevenlabs_voice_id,
+            model_id=elevenlabs_model_id
+        )
+
+        stream(audio_stream)
+
+
+    # pyttsx3 code
+    elif engine.lower() in ("pyttsx3", "offline", "free offline"):
+        
+        engine_pyttsx3 = pyttsx3.init()
+        engine_pyttsx3.say(text_to_procces)
+        engine_pyttsx3.runAndWait()

pyrospeak-0.0.1/pyrospeak.egg-info/PKG-INFO

@@ -0,0 +1,73 @@
+Metadata-Version: 2.4
+Name: pyrospeak
+Version: 0.0.1
+Summary: Simple TTS & STT wrapper with multiple engines
+Author: Mureșan Robert
+License: MIT
+Project-URL: Homepage, https://github.com/Robertinoos13/PyroSpeak-Library
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: pyttsx3
+Requires-Dist: gTTS
+Requires-Dist: pygame
+Requires-Dist: numpy
+Requires-Dist: sounddevice
+Requires-Dist: whisper
+Requires-Dist: faststt
+Requires-Dist: elevenlabs
+
+# `PyroSpeak` 🗣️
+
+`PyroSpeak` is a simple and flexible Python library for Text-to-Speech (TTS) and Speech-to-Text (STT), designed to work with multiple engines, both online and offline, using a clean and beginner-friendly API.
+
+It aims to provide a single, unified interface for common speech tasks without forcing you to deal with low-level audio details.
+
+## Features
+
+- Multiple TTS engines (online & offline)
+- Multiple STT engines (FastSTT, Whisper)
+- Minimal and intuitive API
+- Suitable for experiments, bots, and small AI projects
+- Works well with real-time audio
+
+## Quick Example
+``` python
+from pyrospeak import speak, record
+
+# Text to Speech
+speak("Hello world!", engine="gtts")
+
+# Speech to Text
+text = record(engine="whisper")
+print(text)
+```
+
+## Supported Engines
+### Text-to-Speech (TTS)
+
+- gTTS (Google Text-to-Speech)
+- pyttsx3 (offline)
+- ElevenLabs (API-based)
+
+### Speech-to-Text (STT)
+
+- FastSTT
+- Whisper (OpenAI)
+
+---
+
+## Configuration
+
+Most functions are configurable through keyword arguments such as:
+- engine
+- language
+- model size / device
+- time limits
+
+Refer to the source code for full parameter lists.
+
+
+## License
+
+MIT License
+

pyrospeak-0.0.1/pyrospeak.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+README.md
+pyproject.toml
+pyrospeak/__init__.py
+pyrospeak/stt.py
+pyrospeak/tts.py
+pyrospeak.egg-info/PKG-INFO
+pyrospeak.egg-info/SOURCES.txt
+pyrospeak.egg-info/dependency_links.txt
+pyrospeak.egg-info/requires.txt
+pyrospeak.egg-info/top_level.txt

pyrospeak-0.0.1/pyrospeak.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

pyrospeak-0.0.1/pyrospeak.egg-info/requires.txt

@@ -0,0 +1,8 @@
+pyttsx3
+gTTS
+pygame
+numpy
+sounddevice
+whisper
+faststt
+elevenlabs

pyrospeak-0.0.1/pyrospeak.egg-info/top_level.txt

@@ -0,0 +1 @@
+pyrospeak

pyrospeak-0.0.1/setup.cfg

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