Welcome to the aiOla Python SDKs repository. This repository contains examples and documentation for various SDKs that integrate with aiOla's Text-to-Speech (TTS) and streaming services.
This example demonstrates how to use the aiOla Streaming SDK to capture live transcripts and handle backend-triggered events.
- Key Features:
- Real-time transcription.
- Event-driven callbacks.
- Internal / External Microphone.
This example shows how to set up keyword spotting using the aiOla Streaming SDK.
- Key Features:
- Spot predefined keywords in live streams.
- Event-driven keyword matching.
en-EN, de-DE, fr-FR, zh-ZH, es-ES, pt-PT
This example demonstrates how to convert text into speech and download the resulting audio file using the aiOla TTS SDK.
- Key Features:
- Converts text into
.wav
audio files. - Supports voice selection.
- Converts text into
This example shows how to stream text-to-speech in real-time, enabling audio playback before the entire text is processed.
- Key Features:
- Real-time TTS streaming.
- Immediate audio playback.
- Clone the repository:
git clone https://github.com/aiola-lab/aiola-python-sdk.git cd aiola-python-sdk
- Follow the instructions in the individual example directories for specific use cases.
To install the SDK, run the following command:
pip install aiola-python-sdk
or locally install the package from the root directory:
create virtual environment:
python -m venv .venv
activate virtual environment:
source .venv/bin/activate
install development dependencies:
pip install wheel build setuptools
Build the package:
python -m build
Install the package:
pip install -e .