Webhooks let your application receive signed inbound HTTP requests from Voice.ai and expose outbound callable endpoints for agent actions.
Prerequisites: API key and an agent configured with webhook settings.
Overview
Voice.ai supports three webhook types. webhooks.events, webhooks.inbound_call, and webhooks.tools use different contracts:
webhooks.events supports secret (write-only on create/update) and has_secret (read-only on fetch).
webhooks.inbound_call supports secret (write-only on create/update) and has_secret (read-only on fetch).
webhooks.tools define outbound API calls and do not use secret.
See Agent Configuration, the Web SDK guide, and the API reference for the same public contract on agent config and call-start requests.
| Type | Direction | Purpose | Auth |
|---|
| Event Webhooks | Inbound: Voice.ai → your URL | Notify your system about call lifecycle events | Use secret for HMAC signature verification |
| Inbound Call Webhook | Inbound: Voice.ai → your URL | Personalize inbound calls with dynamic_variables | Use secret for HMAC signature verification |
| Webhook Tools | Outbound: Voice.ai calls your API | Let the agent invoke your application during a call | Use auth_type/auth_token/headers for request authentication |
| Event | Description |
|---|
call.started | Call has connected and the agent is ready |
call.completed | Call has ended, includes transcript and usage data |
When configured, your server receives an HTTP POST request for each event with a JSON payload containing event details.
Event Webhooks
Configuration
Add event webhook configuration to your agent’s config.webhooks.events object:
{
"name": "My Agent",
"config": {
"prompt": "You are a helpful assistant.",
"webhooks": {
"events": {
"url": "https://your-server.com/webhooks/voice-events",
"secret": "your-signing-secret",
"events": ["call.started", "call.completed"],
"timeout": 5,
"enabled": true
}
}
}
}
Event configuration parameters
events supports required/optional fields: required url; optional secret, events, timeout (default 5), enabled (default true). Omit optional fields to use defaults.
| Parameter | Type | Required | Default | Description |
|---|
url | string | Yes | - | Your webhook endpoint URL (must be HTTPS in production) |
secret | string | No | null | HMAC-SHA256 signing secret for payload verification |
has_secret | boolean | No | false | Whether a signing secret is configured (read-only on fetch) |
events | array | No | [] | Event types to receive. Empty array = all events |
timeout | number | No | 5 | Request timeout in seconds (1-30) |
enabled | boolean | No | true | Whether webhook notifications are active |
Event Payloads
All webhook events share a common structure with top-level fields and event-specific data:
| Field | Type | Description |
|---|
event | string | Event type (call.started, call.completed) |
timestamp | string | ISO 8601 timestamp of when the event occurred |
call_id | string | Unique identifier for the call |
agent_id | string | Agent handling the call |
data | object | Event-specific additional data |
call.started
Sent when a call connects and the agent is ready to interact.
{
"event": "call.started",
"timestamp": "2025-02-03T14:30:00.000Z",
"call_id": "call_abc123",
"agent_id": "agent_456",
"data": {
"call_type": "sip_inbound",
"started_at": "2025-02-03T14:30:00.000Z",
"from_number": "+14155551234",
"to_number": "+14155559876"
}
}
data fields:
| Field | Type | Description |
|---|
call_type | string | "web", "sip_inbound", or "sip_outbound" |
started_at | string | ISO 8601 timestamp |
from_number | string | Caller’s phone number (SIP calls only) |
to_number | string | Called phone number (SIP calls only) |
from_number and to_number are only included for SIP (phone) calls. Web calls do not have these fields.
call.completed
Sent after the call ends and all data has been processed. Includes transcript and usage information.
{
"event": "call.completed",
"timestamp": "2025-02-03T14:35:00.000Z",
"call_id": "call_abc123",
"agent_id": "agent_456",
"data": {
"call_type": "sip_inbound",
"duration_seconds": 300.5,
"credits_used": 15.25,
"transcript_uri": "https://storage.example.com/transcripts/call_abc123.json",
"transcript_summary": "Customer inquired about pricing for the enterprise plan...",
"from_number": "+14155551234",
"to_number": "+14155559876"
}
}
data fields:
| Field | Type | Description |
|---|
call_type | string | "web", "sip_inbound", or "sip_outbound" |
duration_seconds | number | Call duration in seconds |
credits_used | number | Credits consumed by this call |
transcript_uri | string | URL to full transcript JSON |
transcript_summary | string | AI-generated summary of the call |
from_number | string | Caller’s phone number (SIP calls only) |
to_number | string | Called phone number (SIP calls only) |
Inbound Call Webhook
webhooks.inbound_call runs before an inbound phone call starts. Use it to personalize a call with dynamic_variables. Do not use it to route a call to a different agent.
Configuration
Add inbound call webhook configuration to your agent’s config.webhooks.inbound_call object:
{
"name": "My Agent",
"config": {
"prompt": "You are a helpful assistant.",
"webhooks": {
"inbound_call": {
"url": "https://your-server.com/webhooks/inbound-call",
"secret": "your-signing-secret",
"timeout": 5,
"enabled": true
}
}
}
}
Inbound call configuration parameters
| Parameter | Type | Required | Default | Description |
|---|
url | string | Yes | - | Your inbound call webhook endpoint URL |
secret | string | No | null | HMAC-SHA256 signing secret for payload verification |
has_secret | boolean | No | false | Whether a signing secret is configured (read-only on fetch) |
timeout | number | No | 5 | Request timeout in seconds (1-30) |
enabled | boolean | No | true | Whether inbound call personalization is active |
Request payload
Voice.ai sends a POST request with the inbound call context:
{
"agent_id": "agent_456",
"call_id": "call_abc123",
"from_number": "+14155551234",
"to_number": "+14155559876"
}
| Field | Type | Description |
|---|
agent_id | string | Agent receiving the inbound call |
call_id | string | Unique identifier for the call |
from_number | string | Caller’s phone number |
to_number | string | Number the caller dialed |
Response payload
Your endpoint can return dynamic_variables:
{
"dynamic_variables": {
"customer_name": "Alice",
"vip": true
}
}
| Field | Type | Description |
|---|
dynamic_variables | object | Optional flat object of string, number, or boolean values |
Omitted fields are allowed. Unused dynamic_variables are ignored by the runtime. See the Web SDK guide for browser-side examples.
Tools are outbound API calls: Voice.ai calls your endpoint. Use auth_type/auth_token/headers (not secret - that is only for signed inbound webhooks like events and inbound_call).
Use config.webhooks.tools to declare callable functions:
{
"name": "My Agent",
"config": {
"prompt": "You are a helpful assistant.",
"webhooks": {
"events": {
"url": "https://your-server.com/webhooks/voice-events",
"secret": "your-signing-secret",
"events": ["call.started", "call.completed"]
},
"tools": [
{
"name": "get_account_status",
"description": "Fetches the latest account status for a customer.",
"url": "https://your-server.com/webhooks/tools/account-status",
"parameters": { "customer_id": "string" },
"method": "POST",
"execution_mode": "sync",
"auth_type": "api_key",
"auth_token": "your-api-key",
"headers": { "X-Service-Version": "2026-02" },
"response": {
"type": "object",
"properties": {
"status": { "type": "string" },
"tier": { "type": "string" }
}
},
"timeout": 10
},
{
"name": "search_knowledge_base",
"description": "Searches the internal KB and returns ranked snippets.",
"url": "https://your-server.com/webhooks/tools/search-kb",
"parameters": {
"query": "string",
"top_k": "number"
},
"method": "GET",
"execution_mode": "async",
"auth_type": "custom_headers",
"headers": {
"X-Internal-Token": "your-internal-token"
},
"timeout": 10
}
]
}
}
}
tools[] supports required/optional fields per tool: required name, description, parameters, url, method, execution_mode, auth_type; optional auth_token, headers, response, timeout (default 10). Omit optional fields to use defaults.
| Parameter | Type | Required | Default | Description |
|---|
name | string | Yes | - | Tool name used in function_name |
description | string | Yes | - | Human-readable tool behavior description |
url | string | Yes | - | Your API endpoint URL |
parameters | object | Yes | - | Tool argument schema |
method | string | Yes | - | GET, POST, PUT, PATCH, or DELETE |
execution_mode | string | Yes | - | sync (wait for response) or async (accept 2xx) |
auth_type | string | Yes | - | none, bearer_token, api_key, or custom_headers |
auth_token | string | No | null | Token for bearer_token or api_key auth |
headers | object | No | {} | Custom headers (for auth_type: custom_headers) |
response | object | No | {} | Expected response shape |
timeout | number | No | 10 | Request timeout in seconds |
Voice.ai makes HTTP requests directly to your tool URL:
- GET: Arguments as query parameters
- POST/PUT/PATCH/DELETE: Arguments as JSON body
Metadata is sent in headers: X-VoiceAI-Request-Id, X-VoiceAI-Tool-Name, X-VoiceAI-Agent-Id, X-VoiceAI-Call-Id
Example GET request:
GET /webhooks/tools/search-kb?query=refund+policy&top_k=3
X-VoiceAI-Request-Id: req_123
X-VoiceAI-Tool-Name: search_knowledge_base
X-VoiceAI-Agent-Id: agent_123
X-VoiceAI-Call-Id: call_123
Example POST request:
POST /webhooks/tools/account-status
Content-Type: application/json
X-VoiceAI-Request-Id: req_456
X-VoiceAI-Tool-Name: get_account_status
X-VoiceAI-Agent-Id: agent_123
X-VoiceAI-Call-Id: call_123
{"customer_id":"cust_987"}
Recommended response (sync mode):
{
"result": {
"status": "active",
"tier": "enterprise"
}
}
auth_type: 'none': no auth headers added.
auth_type: 'bearer_token': sends Authorization: Bearer <auth_token>.
auth_type: 'api_key': sends X-API-Key: <auth_token>.
auth_type: 'custom_headers': sends your configured headers map.
execution_mode: 'sync': waits for downstream response body; non-2xx fails the tool call.
execution_mode: 'async': treats any 2xx as accepted and does not require a response payload.
webhooks.events and webhooks.inbound_call requests include:
| Header | Description |
|---|
Content-Type | application/json |
X-Webhook-Timestamp | Unix timestamp of when the request was signed |
X-Webhook-Signature | HMAC-SHA256 signature (only if events.secret or inbound_call.secret is configured) |
Signature Verification (Event and Inbound Call Webhooks)
webhooks.events and webhooks.inbound_call use secret for HMAC-SHA256. If you configure either secret, verify signatures to ensure requests are from Voice.ai. Tool webhooks use auth_type/auth_token/headers instead and do not use HMAC.
The signature is computed as:
HMAC-SHA256(secret, "{timestamp}.{payload}")
Where:
timestamp is the value from X-Webhook-Timestamp header
payload is the raw JSON request body
Verification Examples
Use the same verifier for both event webhooks and inbound call webhooks.
import hmac
import hashlib
import time
def verify_webhook(request_body: bytes, headers: dict, secret: str) -> bool:
"""Verify webhook signature and timestamp."""
signature = headers.get('X-Webhook-Signature')
timestamp = headers.get('X-Webhook-Timestamp')
if not signature or not timestamp:
return False
# Reject requests older than 5 minutes (replay attack prevention)
if abs(time.time() - int(timestamp)) > 300:
return False
# Compute expected signature
message = f"{timestamp}.{request_body.decode()}"
expected = hmac.new(
secret.encode(),
message.encode(),
hashlib.sha256
).hexdigest()
# Constant-time comparison
return hmac.compare_digest(expected, signature)
# Flask example
from flask import Flask, request, jsonify
app = Flask(__name__)
WEBHOOK_SECRET = "your-signing-secret"
@app.route('/webhooks/voice-events', methods=['POST'])
def handle_webhook():
if not verify_webhook(request.data, request.headers, WEBHOOK_SECRET):
return jsonify({"error": "Invalid signature"}), 401
event = request.json
event_type = event.get('event')
if event_type == 'call.started':
print(f"Call started: {event['call_id']}")
elif event_type == 'call.completed':
print(f"Call completed: {event['call_id']}, duration: {event['data']['duration_seconds']}s")
return jsonify({"status": "ok"}), 200
Retry Logic
Failed webhook deliveries are retried with exponential backoff:
| Attempt | Delay |
|---|
| 1 | Immediate |
| 2 | 1 second |
| 3 | 2 seconds |
| 4 | 4 seconds |
| 5 | 8 seconds |
Retries stop after 5 attempts or on receiving a 4xx response (except 429 rate limit).
Idempotency: Your webhook handler should be idempotent. The same event may be delivered multiple times due to retries. Use call_id to deduplicate events.
Best Practices
- Always verify signatures in production to prevent spoofed requests
- Respond quickly with a 2xx status code within 5 seconds to avoid retries
- Process asynchronously - queue events for processing rather than blocking the response
- Handle duplicates - use
call_id to deduplicate in case of retries
- Check timestamps - reject signed requests older than 5 minutes to prevent replay attacks
- Use HTTPS - ensure your webhook endpoint uses TLS encryption
Filtering Events
You can filter which events you receive by specifying the events array:
{
"webhooks": {
"events": {
"url": "https://your-server.com/webhooks",
"events": ["call.completed"]
}
}
}
This configuration only receives call.completed events. Leave events empty or omit it to receive all event types.
Testing Webhooks
You can test your webhook endpoint using the Test Webhook endpoint:
curl -X POST "https://api.voice.ai/api/v1/agent/{agent_id}/webhook/test" \
-H "Authorization: Bearer YOUR_API_KEY"
This sends a test event to your configured webhook URL and returns the delivery result.
You can test an individual webhook tool using the test tool endpoint:
curl -X POST "https://api.voice.ai/api/v1/agent/{agent_id}/webhook/test-tool/get_account_status" \
-H "Authorization: Bearer YOUR_API_KEY"
This sends a sample function_call payload for the specified tool and returns the delivery result.
For local development, use a tunnel service like ngrok to expose your local server:
ngrok http 3000
# Use the ngrok URL as your webhook URL during development
Next Steps
- Agent Configuration - Configure prompts,
dynamic_variables, and webhook settings
- Web SDK - Pass
dynamicVariables from the browser and configure webhooks through the SDK
- Analytics - View call history and metrics
- API Reference - Complete API documentation