Realtime

Like a realtime voice API - except the brain is already trained on your use case. The full speech loop (STT, VAD, barge-in, TTS) plus your agent, served as one session. Your app or telephony connects; Unpod runs the conversation.

How it connects

A Speech Pipe bundles a voice profile with an agent. Sessions reach it from the web over WebSocket or from a phone number over SIP - same agent, same behaviour, either way.

Go live in 3 steps

1. Create a Speech Pipe

pipe = await client.pipes.create(
    name="Support Bot",
    voice_profile="vp_en_female_hd",   # from voice_profiles.list()
    agent_id="my-bot",
)

2. Connect a session

Web / mobile
Telephony / SIP

import { UnpodSession } from "@unpod/web-sdk";

const session = new UnpodSession({ token });  // short-lived token from your backend
await session.connect();                      // mic + speaker, full duplex
session.on("agent_reply", (text) => console.log("Agent:", text));

Mint tokens server-side with client.sessions.create_token(pipe_id=...). Protocol and auth: WebSocket sessions.

Raw audio-frame WebSocket streaming for custom transports is on the roadmap.

3. Test it

Call the number, or open your web session and talk. Recordings and transcripts land automatically - see Recordings & Transcripts.

Go deeper

WebSocket sessions

Session tokens, events, capabilities.

Voice profiles

STT + TTS bundles per language, with failover.

Speech pipes

The unit that wires voice, agent, and numbers.

Bring your agent

Point a pipe at any HTTP endpoint or LangChain brain.

PhoneYour trained agent, on a live phone number. Nothing to host.

Start Here

Use it like a model

How it connects

Go live in 3 steps

1. Create a Speech Pipe

2. Connect a session

3. Test it

Go deeper

WebSocket sessions

Voice profiles

Speech pipes

Bring your agent

​How it connects

​Go live in 3 steps

​1. Create a Speech Pipe

​2. Connect a session

​3. Test it

​Go deeper

WebSocket sessions

Voice profiles

Speech pipes

Bring your agent

How it connects

Go live in 3 steps

1. Create a Speech Pipe

2. Connect a session

3. Test it

Go deeper