A Text To Speech engine with realistic voices developed entirely in Python and powered by Microsoft Azure as Python Package
- Linux:
pip3 install rspeechpy- Windows:
pip install rspeechpy- List all avaible voices:
import asyncio
from rspeechpy import Engine
# Declaration
speech = Engine()
async def example():
names = await speech.giveVoicesList()
for name in names:
print(name['FriendlyName']) # Describe voice's name & language.
print(name['ShortName']) # Return "key" to use that voice.
# Running
app = asyncio.get_event_loop()
app.run_until_complete(example())- Create a synthesize from text (Generate .mp3 audio):
import asyncio
from rspeechpy import Engine
# Declaration
speech = Engine()
async def example():
await speech.setVoice('es-ES-ElviraNeural')
await speech.setRate(5)
await speech.setPitch(5)
await speech.setVolume(5)
text = "Hola esto es una prueba de texto a voz"
await speech.synthesize(text, 'audio.mp3')
# Running
app = asyncio.get_event_loop()
app.run_until_complete(example())| Parameter | Type | Description |
|---|---|---|
api_key |
string |
Non-Required |
