Metadata-Version: 2.4
Name: dataspike-livekit-plugins
Version: 1.2.15
Summary: Dataspike deepfake detection plugin for LiveKit Agents
Project-URL: Documentation, https://docs.dataspike.io
Project-URL: Website, https://dataspike.io/
Project-URL: Source, https://github.com/dataspike-io/agents
Author-email: LiveKit <hello@livekit.io>
License-Expression: Apache-2.0
Keywords: dataspike,livekit,realtime,video,webrtc
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Multimedia :: Video
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9.0
Requires-Dist: betterproto==2.0.0b6
Requires-Dist: livekit-agents>=1.2.15
Requires-Dist: protobuf>=3.20.0
Description-Content-Type: text/markdown

# Dataspike Deepfake Detection Plugin for LiveKit Agents

This plugin integrates [Dataspike](https://dataspike.io/) with LiveKit Agents to provide **real-time deepfake detection**.  
It enables detection of synthetic or manipulated media during live or recorded video streams.

## Installation

```bash
pip install livekit-plugins-dataspike
```

## Prerequisites

You’ll need a **Dataspike API key**. Set it as an environment variable before running your agent:

```bash
export DATASPIKE_API_KEY="your_api_key_here"
```

## Usage Example

```python
from livekit.plugins import dataspike
from livekit.agents import AgentSession, Agent

async def entrypoint(ctx):
    await ctx.connect()
    session = AgentSession(...)
    detector = dataspike.DataspikeDetector()
    await detector.start(session, room=ctx.room)
    await session.start(agent=Agent(instructions="Talk to me!"), room=ctx.room)
```
 
## Links

- [Dataspike API](https://docs.dataspike.io/api)
- [LiveKit Agents SDK](https://github.com/livekit/agents)
