GPU Similarity Search/Databases, Vector & Storage
Connect FAISS (Meta) to IntelDialix voice agents
High-performance acoustic embedding similarity search for voice biometric speaker identification.
In short
You connect FAISS (Meta) to IntelDialix in two directions. When a call starts or ends, IntelDialix sends a signed webhook to FAISS (Meta) with the transcript and outcome. During a call, an agent can reach FAISS (Meta) through a custom tool — an HTTP request you define — to look up or update information. No SDK is needed; it is plain HTTPS and JSON.
- FAISS (Meta)
- IntelDialix
- AI voice agent
- Webhooks
- FAISS C++ & Python Bindings
- HTTPS
- JSON
How it works
How information moves between a live phone call and FAISS (Meta).
- 01
A call reaches your agent
A caller dials a Twilio or SIP number assigned to the agent, or the agent places an outbound call from a campaign.
Twilio / SIP number → IntelDialix agent
- 02
The agent uses FAISS (Meta) mid-call
When the conversation needs data, the agent runs a custom tool: an HTTP request to FAISS (Meta) with the details it has collected.
Custom tool → FAISS C++ & Python Bindings
- 03
The call ends with a record
IntelDialix keeps the recording, transcript and post-call analysis for the conversation in your call history.
Recording · transcript · analysis
- 04
FAISS (Meta) receives the result
A signed webhook delivers the call event to your FAISS (Meta) endpoint, and is retried automatically if the delivery fails.
HTTPS POST · X-Dialix-Signature
At a glance
Key figures
- Voice engines
- ElevenLabs · Vapi · Gemini
- Choose the engine per agent and compare them on real calls.
- Telephony
- Twilio & SIP
- Use numbers you already have, for inbound and outbound calls.
- Call events
- Signed webhooks
- HMAC-SHA256 signature on every delivery, retried on failure.
- Starter plan
- $14 / month
- One agent, one number and 100 calls a month.
Example
// Verify an IntelDialix webhook before trusting it in FAISS (Meta).
// Header: X-Dialix-Signature: t=<unix seconds>,v1=<hex>
// where v1 = HMAC-SHA256(secret, "<t>.<raw request body>")
import crypto from 'node:crypto';
export function verifyDialixWebhook(rawBody, signatureHeader, secret) {
const parts = Object.fromEntries(
signatureHeader.split(',').map((kv) => kv.split('='))
);
const expected = crypto
.createHmac('sha256', secret)
.update(`${parts.t}.${rawBody}`)
.digest('hex');
const valid =
typeof parts.v1 === 'string' &&
parts.v1.length === expected.length &&
crypto.timingSafeEqual(Buffer.from(parts.v1), Buffer.from(expected));
const fresh = Math.abs(Date.now() / 1000 - Number(parts.t)) < 300;
return valid && fresh;
}
// Body: { "event": "call.completed", "payload": { ... }, "timestamp": "..." }Check the signature before acting on an event in FAISS (Meta). The secret is the one you set when you add the webhook in IntelDialix settings.
FAQ
Frequently asked questions
How does IntelDialix connect to FAISS (Meta)?
Through webhooks and custom tools. IntelDialix posts call events to a FAISS (Meta) endpoint you choose, and agents can call FAISS (Meta) during a conversation using an HTTP tool you configure in the agent editor.
Which events can FAISS (Meta) receive?
IntelDialix sends events such as call.initiated, call.inbound, call.completed, call.failed, campaign.started, campaign.completed. Each delivery includes a JSON payload and an X-Dialix-Signature header you can verify with your webhook secret.
Do I need a developer to set this up?
You need an HTTPS endpoint in FAISS (Meta) that can receive webhooks — many tools provide one — and, for mid-call actions, an endpoint the agent can call. Building the agent itself needs no code.
Keep exploring
Related pages
- integrationNeon Postgres Voice AI IntegrationInstant database branching for testing new voice agent configurations against production telephony datasets.
- integrationDatabricks Voice AI IntegrationDelta Lake storage and Apache Spark processing for enterprise-scale speech analytics and customer retention modeling.
- integrationSupabase Voice AI IntegrationStore caller records, dynamic variables, and conversation state in Postgres with real-time vector embeddings.
- integrationPinecone Voice AI IntegrationVector search that retrieves knowledge-base snippets for the agent while the caller is speaking.
- integrationWeaviate Voice AI IntegrationHybrid BM25 and vector search providing instantaneous factual grounding for phone agent technical questions.
Put an agent on the phone today.
Create a free account to explore the dashboard. Plans start at $14 a month for one agent and 100 calls.