Behavioral Signals Python SDK

The Behavioral Signals Python SDK makes it easy to integrate our API into your applications. With a few lines of code, you can access real-time and batch analysis for both behavioral insights (such as emotion, engagement, and speaking style) and deepfake detection in speech.

Whether you’re building voice analytics, enhancing contact center tools, or detecting synthetic media, our SDK supports both streaming and file-based audio input modes to fit your use case.

🐍 Installation from PyPI

You can install the Behavioral Signals SDK from PyPI with:

pip install behavioralsignals

Simple usage:

from behavioralsignals import Client

cid = "<your-cid>"
token = "<your-api-token>"
file_path = "/path/to/audio.wav"

client = Client(cid, token)

response = client.behavioral.upload_audio(file_path=file_path)
output = client.behavioral.get_result(pid=response.pid)

We currently provide two main APIs:

the Behavioral API for analyzing human behavior through voice, and
the Deepfakes API for detecting deepfake audio content in human speech.

Both APIs support batch and streaming modes, allowing you to send audio files or streams for analysis and receive results in real-time or after processing. You can also find more detailed examples for both batch and streaming in the examples directory.

The next pages of this documentation contain snippets on how to use the SDK for sending/streaming audios and retrieving the results.

⭐ Github repo

Feel free to visit our Github repo at https://github.com/BehavioralSignalTechnologies/behavioralsignals-python

You can also raise any issues there, and on our Discord server