Vonage Voice/Video API AI connectors (Audio Connector) + AI Studio
Vonage's Voice and Video APIs can stream call audio over WebSocket (Audio Connector, 8/16/24 kHz PCM) or WebRTC (Video Connector) to your own AI pipeline, with a Pipecat serializer; AI Studio is the low-code agent builder priced per session.
Overview
Best for: Teams already on Vonage telephony or Video API who want to plug in their own AI pipeline.
At a glance
Voice API per-minute rates could not be verified. AI Studio (low-code) is priced per session plus per-request NLU charges.
Linear PCM 8/16/24 kHz over WebSocket
Same (bidirectional)
Depends on your models.
No verified number.
Global.
Not verified in this research.
Features
- telephony
- WebSocket audio streaming
- Pipecat serializer
- per-second billing on Voice API (vendor claim)
- low-code builder (AI Studio)
Pricing
| What | Price | Unit |
|---|---|---|
| Voice API minutes | Not verified | per minute (billed per second) |
| AI Studio NLU / Knowledge AI | about $0.007-$0.008 | per request |
Could not verify current Vonage per-minute voice rates. Vapi's pricing page lists Vonage telephony at $0.00814/min as a pass-through reference.
Free tier: Not verified.
Source: developer.vonage.com
Setup
- Create a Vonage application with Voice (and/or Video) capability and a number.
- For phone calls, answer with an NCCO 'connect' action to a websocket endpoint, or use the Audio Connector SDK for Video sessions.
- Run your STT/LLM/TTS pipeline on the WebSocket (Pipecat has a Vonage serializer) and stream PCM back.
Endpoint
Voice API answer_url returning NCCO; WebSocket endpoint you hostAuthentication
Application ID + private key (JWT)
Quick start javascript
// Express answer_url: connect an inbound Vonage call to your AI WebSocket (16 kHz linear PCM)
import express from "express";
const app = express();
app.get("/answer", (req, res) => {
res.json([
{ action: "talk", text: "This call is with an AI assistant and may be recorded." },
{ action: "connect",
endpoint: [{ type: "websocket", uri: "wss://ai.example.com/vonage",
"content-type": "audio/l16;rate=16000",
headers: { caller: req.query.from } }] }
]);
});
app.listen(3000);Written from the current docs. Check the vendor's SDK version before you ship.
Warnings
Pricing not verified
Vonage's voice pricing page could not be fetched in this research; confirm rates in the dashboard.
AI Studio priced per session, not per minute
Sessions plus per-request NLU/Knowledge AI charges plus standard voice minutes; professional services packs start at $3,300/month.
NCCO snippet from general knowledge
The websocket connect NCCO shape is long-standing but was not re-verified against current docs here.
Bring your own AI stack
Connectors only move audio; all STT/LLM/TTS costs and latency are yours.
Plus 12 warnings that apply to all platforms and telephony APIs. See category warnings.
Limits
- AI Studio fair use: average max 50 events per session
Models and products
| Name | Status |
|---|---|
| Audio Connector Server SDK | GA |
| Video Connector Server SDK | GA |
| AI Studio | GA |
Docs and sources
Docs
Sources used
- developer.vonage.com/en/video/ai-connectors/overview
- developer.vonage.com/en/blog/introducing-audio-connector-sdk-and-pipecat-serial...
- vonage.com/communications-apis/ai-studio/pricing/
All per-minute voice rates; AI Studio tier prices; NCCO websocket fields.