> ## Documentation Index
> Fetch the complete documentation index at: https://docs.roark.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Custom Integrations
> Send calls from any platform using our API and SDKs
## Overview
Not using one of our pre-built integrations? No problem. Send call data from any voice AI platform or custom application — just provide an audio file and Roark handles the rest: transcription, speech analysis, sentiment detection, and metric collection.
***
## Send a Call
Install the [Node.js SDK](/documentation/sdks/node-sdk):
```bash theme={"theme":{"light":"everforest-light","dark":"everforest-dark"}}
npm install @roarkanalytics/sdk
```
```typescript theme={"theme":{"light":"everforest-light","dark":"everforest-dark"}}
import Roark from '@roarkanalytics/sdk'
const client = new Roark({
bearerToken: process.env.ROARK_API_BEARER_TOKEN,
})
const call = await client.call.create({
recordingUrl: 'https://your-storage.com/call-recording.mp3',
startedAt: '2024-01-15T10:00:00Z',
interfaceType: 'PHONE',
callDirection: 'INBOUND',
agent: {
name: 'Support Agent',
customId: 'custom-agent-1',
},
customer: {
phoneNumberE164: '+1234567890',
},
properties: {
department: 'sales',
region: 'us-east',
},
})
```
Install the [Python SDK](/documentation/sdks/python-sdk):
```bash theme={"theme":{"light":"everforest-light","dark":"everforest-dark"}}
pip install roark-analytics
```
```python theme={"theme":{"light":"everforest-light","dark":"everforest-dark"}}
import os
from roark_analytics import Roark
client = Roark(
bearer_token=os.environ.get("ROARK_API_BEARER_TOKEN"),
)
call = client.call.create(
recording_url="https://your-storage.com/call-recording.mp3",
started_at="2024-01-15T10:00:00Z",
interface_type="PHONE",
call_direction="INBOUND",
agent={
"name": "Support Agent",
"customId": "custom-agent-1",
},
customer={
"phoneNumberE164": "+1234567890",
},
properties={
"department": "sales",
"region": "us-east",
},
)
```
Use the [REST API](/api-reference/introduction) directly:
```bash theme={"theme":{"light":"everforest-light","dark":"everforest-dark"}}
curl --request POST \
--url https://api.roark.ai/v1/call \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"recordingUrl": "https://your-storage.com/call-recording.mp3",
"startedAt": "2024-01-15T10:00:00Z",
"interfaceType": "PHONE",
"callDirection": "INBOUND",
"agent": {
"name": "Support Agent",
"customId": "custom-agent-1"
},
"customer": {
"phoneNumberE164": "+1234567890"
},
"properties": {
"department": "sales",
"region": "us-east"
}
}'
```
Once a call is created, it appears in [Call History](/documentation/observability/live-monitoring) and is automatically transcribed and analyzed.
***
## What You Can Send
| Data | Description |
| :----------------------- | :----------------------------------------------------------- |
| **Audio file** | MP3, WAV, M4A, or FLAC — via public URL or base64 |
| **Metadata** | Agent info, customer details, call direction, interface type |
| **Custom properties** | Arbitrary key-value pairs for filtering and segmentation |
| **Tool calls** | Function/tool invocations made during the conversation |
| **Pre-transcribed text** | If you already have a transcript, send it along |
### Audio Requirements
| Spec | Requirement |
| :-------------- | :---------------------------------------- |
| **Format** | MP3, WAV, M4A, or FLAC |
| **Sample Rate** | 8kHz or higher |
| **Channels** | Mono or stereo |
| **Duration** | Up to 2 hours |
| **File Size** | Max 500MB |
| **Access** | Publicly accessible URL or base64 encoded |
***
## What Happens Next
Once a call is ingested, Roark automatically:
1. **Transcribes and analyzes** the conversation — speech patterns, sentiment, 64+ emotions, interruptions, and more
2. **Runs metric collectors** — any active [metric collectors](/documentation/metrics/metric-collectors) collect metrics automatically (LLM evaluations, compliance checks, custom KPIs)
3. **Makes it searchable** — the call appears in [Call History](/documentation/observability/live-monitoring) with full filtering by properties, agent, duration, and more
***
## Use With Simulations
Agents created via the API can also be used in [simulations](/documentation/simulation-testing/overview). When you send calls with an `agent.customId`, Roark creates or matches an agent record that you can then target in simulation run plans — useful for testing custom-built voice agents that aren't on a pre-built platform.
***
## MCP Server
If you use an AI-powered development environment, the [Roark MCP Server](/documentation/sdks/mcp-server) gives your AI assistant direct access to the Roark API — including creating calls, querying metrics, and managing agents — without writing integration code manually.
***
## Getting Started
Create an API key in your [Roark dashboard](/documentation/getting-started/api-keys)
Upload an audio file using the SDK or REST API above
Set up [metric collectors](/documentation/metrics/metric-collectors) to automatically collect metrics on every call
Browse calls in [Call History](/documentation/observability/live-monitoring), build [reports](/documentation/observability/reports), and create [dashboards](/documentation/observability/dashboards)
***
## Resources
Send OpenTelemetry traces from any platform
Full SDK guide and reference
Full SDK guide and reference
Complete REST API documentation