What the Speech Stack Does
The Speech Stack gives your agent voice. It handles everything between the user’s audio and your agent’s text logic. Your agent receives plain text. It returns plain text. The Speech Stack handles everything else: transcription, synthesis, VAD, barge-in detection, endpointing, and transport.Two Ways Users Connect
Phone / Telephony
Users dial a phone number. Unpod handles SIP, PSTN, number provisioning, and routing. No carrier account or SIP trunk needed.
Browser / App
Users connect from a web app or mobile app via the Unpod Web SDK. Same speech pipeline - no phone number required.
How Audio Flows
1
User connects
Via a phone number (PSTN/SIP) or directly from a browser/app using the Web SDK.
2
Speech pipeline runs
Unpod transcribes audio (STT), detects turn end (VAD + endpointing), and handles barge-in interruptions. Your agent gets clean text.
3
Your agent responds
The Unpod orchestrator dispatches the session to your
AgentRunner. Your entrypoint runs, your dialog machine produces a text reply.4
Reply synthesised
Unpod converts the reply to speech (TTS) and streams it back to the user.
5
Session ends
Transcript, metrics, and recording are stored and queryable via the management API.
Core Building Blocks
Voice Profiles
Choose STT and TTS providers. Pre-built profiles or custom combinations with automatic failover.
Speech Pipe
Bundle a voice profile, recording settings, and connection attachments, then point the pipe at your agent.
Phone Numbers
Provision numbers directly or bring your own. Attach to a Speech Pipe for inbound calls.
SDK Setup
Install
unpod, run your AgentRunner, and accept sessions from any source.Quickstart Paths
Next Steps
Quickstart
End-to-end: agent running and accepting sessions in under 10 minutes.
SuperDialog Integration
Drive conversations with structured flows and tools.