PyroSpeak is a small Python wrapper library that uses big technologies like gTTS, pyttsx3, ElevenLabs, FastSTT and Whisper for text-to-speech (TTS) and speech-to-text (STT) transformation.
It is a useful library if you want live STT transformation from microphone or TTS using a string value, each type of transformation being in a single function.
from pyrospeak import speak, record
# Say anything on your microphone to generate a string
text = record()
# Put your hardware to read it vocally what you sayed (be sure you volume to be ON)
speak(text)- Focus on simplicity and quality
- Record LIVE audio from the microphone using just one simple function:
record() - Generate audio based on text, using just a simple function, nothing more:
speak() - It is built on larger and more well-known frameworks/technologies, specifically made for TTS/STT transformation:
gTTS,pyttsx3,ElevenLabs,FastSTTandWhisper
Considering that at the current time (March 2, 2026), PyroSpeak is not yet on PyPI, installation is done directly from this repository on GitHub.
-
Press the key combination Win + R
-
Type '
cmd' and click enter -
Copy-paste this line into CMD:
pip install git+https://github.com/Robertinoos13/PyroSpeak-Library.git#subdirectory=pyrospeak-pack
You also have the option of installing
PyroSpeakby installing its files from the repository, then placing them together with your fixed project in the same folder, but this is neither recommended nor flexible for multiple projects.
| function | used for |
|---|---|
speak() |
text-to-speech |
record() |
speech-to-text |
Well, the currently available python functions have a parameter that requires a string value, this being the 'engine' parameter.
Quick example:
from pyrospeak import speak
speak(text_to_procces="Hello, I am a code that can speak. Nice, no?",
engine="gTTS")This will display all the Python technologies for TTS/STT that were used for PyroSpeak:
| tehnology name | used for | github repository (link & name) |
|---|---|---|
| gTTS | text-to-speech | gTTS |
| pysttsx3 | text-to-speech | pysttsx3 |
| Whisper | speech-to-text | whisper |
| FastSTT | speech-to-text | faststt |
| ElevenLabs | text-to-speech | elevenlabs-python |
| Pygame | text-to-speech (playing audio) | pygame |

