Skip to main content
Omni agents can speak a greeting message the instant a call connects, turn 0, before the caller says anything. Store it on an agent profile in the console (or POST /v1/agents) and connect with session_label={agent_id}; the engine loads persona, voice, and greeting from that profile.
Greeting playback is live on Omni. The same field works inline in a post-handshake configure frame if you are not using agent profiles.
1

Create or open an agent

In console.pyai.com → Agents → New agent or open an existing profile.
2

Set the greeting message

Under Identity & voice, fill in Opening greeting, e.g.
Pick a voice on the same tab. Save changes.
3

Test in the browser

Save, then open Review & test. The console opens an Omni session with your agent profile and plays turn-0 audio in your speakers.
4

Connect from your app

Use the API integration tab URL:
Authorize with your API key (omni:session scope). The greeting plays automatically, you do not send it again in configure unless you want to override per call.
When Record calls is enabled, set Recording disclosure under Identity & voice → Advanced & compliance. The engine speaks the consent line before recording starts, then plays your greeting. The API requires a meaningful disclosure when recording is enabled.

API

Update an existing profile with POST /v1/agents/{id}. To create the profile first, follow the Agents API guide.
For approved opening variations, save greeting_variants (up to 15 strings). PyAI selects an opening when resolving a new call profile. An empty list or null falls back to greeting; the consent line never rotates. The console’s Generate variations action creates a draft to review before saving. The order is recording disclosure, greeting, then conversation. To change only the greeting, omit the recording fields. Save changes and start a new call.

Inline configure (no agent profile)

If you connect without session_label, pass greeting in the first configure frame after the WebSocket opens:
See Omni protocol for the full configure surface.

Pre-roll alternative (client-side TTS)

Before native greeting shipped, apps synthesized the opening line with Speak and played it locally. That pattern still works but is optional now; prefer the native greeting field for simpler wiring. Details: Browser voice agent, Make the agent speak first.

Browser voice agent

Full browser Omni walkthrough.

Twilio phone agent

Greeting on inbound PSTN calls.

Omni protocol

greeting, consent_line, and configure frames.

Post-call extraction

Capture structured data after the greeting call.