https://github.com/ashad001/voice-pipeline-agent
https://github.com/ashad001/voice-pipeline-agent
Last synced: 6 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/ashad001/voice-pipeline-agent
- Owner: Ashad001
- License: apache-2.0
- Created: 2024-12-03T11:53:04.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2024-12-03T13:48:25.000Z (10 months ago)
- Last Synced: 2025-02-03T10:46:31.552Z (8 months ago)
- Language: TypeScript
- Size: 218 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Python Voice Agent
Deploy a sandbox app
•
LiveKit Agents Docs
•
LiveKit Cloud
•
Blog
A basic example of a voice agent using LiveKit and Python.
## Dev Setup
Clone the repository and install dependencies to a virtual environment:
```console
cd voice-pipeline-agent-python
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
```
Set up the environment by copying `.env.example` to `.env.local` and filling in the required values:
- `LIVEKIT_URL`
- `LIVEKIT_API_KEY`
- `LIVEKIT_API_SECRET`
- `OPENAI_API_KEY`
- `DEEPGRAM_API_KEY`
You can also do this automatically using the LiveKit CLI:
```console
lk app env
```
Run the agent:
```console
python3 agent.py dev
```
This agent requires a frontend application to communicate with. You can use one of our example frontends in [livekit-examples](https://github.com/livekit-examples/), create your own following one of our [client quickstarts](https://docs.livekit.io/realtime/quickstarts/), or test instantly against one of our hosted [Sandbox](https://cloud.livekit.io/projects/p_/sandbox) frontends.