Skip to main content

​
Activating Conversation Mode

Whoever administers the Digital Twin can make Convo Mode the default experience: with Start Immersive Mode by Default enabled (Instance Settings → Voice, or the admin instance editor), visitors land on a tap-to-start screen right after signing in — the tap grants microphone access and begins the conversation. Anyone can exit to the classic chat, and each visitor’s last choice (voice or text) is remembered on their device for future visits. Full-screen behaviour is covered below (see Kiosk lock).
1

Locate convo mode icon

From the main interface, look for the Conversation icon on the text input barConvo Mode Ui Locations Web
2

Enable microphone

Allow microphone use in the browserConvo Microphone Settings Web
3

Start speaking

Click the start button and begin talking. Your Digital Twin will listen and respond with voice.Convo Mode Start Button Web

​
The Convo Mode panel

Once you launch Convo Mode, a floating panel appears over your conversation — Pria’s avatar orb with the controls beneath it.
The Convo Mode floating panel showing Pria's circular avatar, a START button, an expand button, a Cedar voice selector, and a close ×.

The Convo Mode panel: the avatar orb with START, the expand (display-mode) button, the voice picker, and a close ×.

​
Display modes

Convo Mode in expanded mode — the avatar orb centered on a full-screen background with START, the display-mode toggle, and the voice selector.

Expanded mode fills the screen for a focused, immersive conversation.

Tap the expand button to grow the panel, and the same button (now Contract) to shrink it back. Pressing Esc also collapses the full-screen view back to the compact panel. On supported devices an administrator can enable true fullscreen immersive mode — and a fullscreen transcript — per Digital Twin in Instance Settings → Voice.
Kiosk lock. If the Twin’s administrator turns on Lock full-screen conversation (Instance Settings → Voice), the collapse button and the Esc key are disabled — ending the call is the only way out of the full-screen view. Starting, ending, and muting the call work exactly as usual. This keeps kiosk screens and embedded experiences in the conversation for the whole session.
Mute and the live transcript appear once a voice session is actually running — press START to see them.

​
Voice Providers

Convo Mode supports several real-time voice and avatar providers. Your administrator selects which provider your Digital Twin uses; see Voice & Realtime Providers for the integration overview and Realtime Voice & Avatars for admin-side configuration.
The default voice provider, powered by OpenAI’s Realtime API.
  • Voice selection — Choose from 10+ built-in voices (Cedar, Marin, Alloy, Ash, and more) directly in the Convo Mode panel
  • Knowing when you’ve finished speaking — Pria listens for the pause at the end of your sentence; an administrator can tune how quickly it jumps in (the setting is called Voice Activity Detection, or VAD)
  • Tool calling — Your Digital Twin can use the tools that work aloud (searching your files, looking things up on the web, and so on) during voice conversations. A few tools are text-only by nature and are left out of a spoken turn.
  • Connector (MCP) support — Connected MCP servers are available during real-time conversations, run by OpenAI itself
  • Usage tracking — how much was said and heard is counted and shown, so you can see what a voice session costs
  • Reasoning support — On GPT-Realtime-2 and newer, the twin’s Voice Reasoning Effort setting decides how much the model thinks before it answers aloud. It is off by default, because thinking time is silence in a conversation. See AI Models for details.

​
Switching voices mid-conversation

You can change the voice at any time during a Convo session — the new voice takes effect on the next response. Open the voice picker in the Convo panel header, pick a new voice, and continue speaking; the running response (if any) finishes in the original voice, then the next turn switches. Switching between providers (OpenAI ↔ GPT-Live ↔ xAI ↔ Gemini Live ↔ ElevenLabs ↔ Cartesia ↔ Anam) is an admin action — the live voice picker only swaps voices within the active provider. On a twin set to Anam, the avatar and its voice are configured together, so changing the voice is an administrator’s change in Instance Settings rather than a pick in the panel.

​
Avatar animation feedback

When an avatar provider is active, the Convo panel includes a few visual cues so you can tell what state Pria is in:

​
Features

Your assistant comes along

Start Convo Mode inside a conversation that runs an assistant and the twin keeps that assistant’s instructions out loud. Where the twin’s administrator has turned on Restrict use of assistants, the in-call assistant menu lets you switch between the allowed assistants, each shown with its picture.

Natural Dialogue Flow

Your digital twin knows how to have actual conversations. It waits for you to finish your thoughts before jumping in, remembers what you’ve been talking about, and lets you ask follow-up questions without having to repeat yourself.

Answers written for speech

A spoken answer isn’t a typed one read out. Your twin works from instructions meant for talking, so it stays in its own voice and gets to the point instead of reciting headings, tables and footnotes that make no sense out loud. When it needs to look something up it says a few words first, so the conversation never goes quiet on you. Typed conversations are unaffected.

Voice Capabilities

When you speak, your words appear as text right away. When your digital twin responds, you’ll hear it speak back to you with a natural-sounding voice. The more you use it, the better it gets at understanding how you talk.

Text Input

Prefer typing? When text input is enabled, you can type messages during a voice conversation instead of speaking. Your Digital Twin responds with both voice and text — ideal for noisy environments or when you need to input precise information.

Multilingual Support

Switch between languages right in the middle of a conversation. Your digital twin will catch on and switch with you, keeping track of what you were talking about.

Knowledge Integration

Your AI assistant automatically references your uploaded documents and custom-built assistants during conversations, providing personalized and contextually relevant responses.

Saved to your history

Each voice conversation is saved in your conversation history as one dialogue, with every turn of the session, so you can read it back later.

​
Provider Comparison

Anam Avatar supplies a lip-synced video face together with its own voice, so a twin is set to Anam instead of to one of the audio-only providers above. OpenAI GPT-Live is a voice layer only. Both answer through your Digital Twin’s own model, like Cartesia, so connector tools reach them the same way.
Connector tools work in voice on every provider — the difference is who runs them. OpenAI runs its own; everywhere else Pria makes the call itself, carrying the signed identity of the person speaking. Your Digital Twin needs connectors configured for any of this to apply; see MCP Server.
Your administrator selects the voice provider for your Digital Twin. Contact your admin if you have questions about which provider is active.

​
Troubleshooting Common Issues

Check permissions and hardware connections. Your microphone needs to be enabled in the browser for Convo Mode to work.
Adjust input sensitivity and check for background noise.
Use headphones or adjust speaker volume.
Speak clearly and check language settings.
Check internet connection and try restarting the conversation.
Provide a brief recap of your previous discussion and pick up from there.
Rephrase using different words or examples.
Explicitly state language changes if the Digital Twin does not pick up on the switch.
If you don’t see voice selection or VAD controls, your Digital Twin is using ElevenLabs as the voice provider. These settings are managed by your administrator in the ElevenLabs dashboard.