> ## Documentation Index
> Fetch the complete documentation index at: https://docs.praison.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Voice Call API
> Twilio voice integration with OpenAI Realtime API
# Voice Call API
The Voice Call API provides Twilio voice integration with OpenAI's Realtime API for voice-based AI interactions.
## Base URL
```
http://localhost:8090
```
## Endpoints
### Status Page
Check if the server is running.
Returns HTML status page
**Response**
```html theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
Praison AI Call Server
Praison AI Call Server is running!
```
***
### Incoming Call Handler
Handle incoming Twilio calls and return TwiML response.
Twilio webhook for incoming calls
**Response (TwiML)**
```xml theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
```
***
### Media Stream WebSocket
WebSocket endpoint for real-time audio streaming between Twilio and OpenAI.
WebSocket for audio streaming
**Connection Flow**
1. Twilio connects to WebSocket
2. Server connects to OpenAI Realtime API
3. Audio streams bidirectionally:
* Twilio → Server → OpenAI (user speech)
* OpenAI → Server → Twilio (AI response)
**Twilio Events**
| Event | Description |
| ------- | ---------------- |
| `start` | Stream started |
| `media` | Audio data chunk |
| `stop` | Stream ended |
**OpenAI Events**
| Event | Description |
| ----------------------------------- | ----------------------- |
| `session.created` | Session initialized |
| `session.updated` | Session config updated |
| `input_audio_buffer.speech_started` | User started speaking |
| `input_audio_buffer.speech_stopped` | User stopped speaking |
| `response.audio.delta` | AI audio response chunk |
| `response.done` | AI response complete |
## Configuration
### Environment Variables
| Variable | Required | Default | Description |
| ------------------ | -------- | ------- | ----------------------------------- |
| `OPENAI_API_KEY` | Yes | - | OpenAI API key with Realtime access |
| `PORT` | No | `8090` | Server port |
| `NGROK_AUTH_TOKEN` | No | - | ngrok token for public URL |
| `PUBLIC` | No | `false` | Enable public URL via ngrok |
### Custom Tools
Create a `tools.py` file in the working directory:
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# tools.py
async def get_weather(location: str) -> dict:
"""Get weather for a location."""
return {"location": location, "temp": "72°F", "condition": "sunny"}
get_weather.definition = {
"name": "get_weather",
"description": "Get current weather for a location",
"parameters": {
"type": "object",
"properties": {
"location": {"type": "string", "description": "City name"}
},
"required": ["location"]
}
}
tools = [(get_weather.definition, get_weather)]
```
## Usage Example
### Start Server
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Basic start
python -m praisonai.api.call
# With public URL
python -m praisonai.api.call --public
# Custom port
python -m praisonai.api.call --port 9000
```
### Twilio Configuration
1. Get your public URL (ngrok or deployed)
2. In Twilio Console:
* Go to Phone Numbers → Your Number
* Set Voice webhook to: `https://your-url.ngrok.io/`
* Method: POST
### Python Usage
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonai.api.call import run_server
# Start the server
run_server(port=8090, use_public=True)
```
## Session Configuration
The server sends this session configuration to OpenAI:
```json theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
{
"type": "session.update",
"session": {
"turn_detection": {
"type": "server_vad",
"threshold": 0.5,
"prefix_padding_ms": 300,
"silence_duration_ms": 200
},
"input_audio_format": "g711_ulaw",
"output_audio_format": "g711_ulaw",
"voice": "alloy",
"tools": [],
"tool_choice": "auto",
"modalities": ["text", "audio"],
"temperature": 0.8
}
}
```
## Related
* [CLI](/docs/cli/cli) - Command-line interface
* [Agent](/docs/sdk/praisonaiagents/agent/agent) - Agent configuration