Skip to main content
Convo Mode is Pria’s live two-way voice surface. Audio streams from the microphone to a speech-to-text engine, through your selected LLM, and back out as spoken audio — with optional animated avatars on top. This page covers the Admin-side setup. For the end-user experience see the user-guide page on Convo Mode.

​
What Convo Mode Is

Once enabled, users see a microphone affordance in the Pria interface that opens a live audio session. The session runs entirely browser-to-provider after Pria mints a short-lived session token — your long-lived API keys never reach the browser. What a session does end-to-end:
  • Captures microphone audio and streams it to the provider.
  • Streams partial transcripts back to the UI (optional).
  • Runs your assistant’s prompt, tools, RAG, and personalization on every turn.
  • Speaks the response back through the provider’s TTS voice.
  • Optionally renders an animated avatar synced to the audio.
Audio frames never traverse the Pria backend in steady state. Pria brokers the session token, then the browser opens a direct connection to the voice provider.

​
Who Can Use Convo Mode

These toggles on the Digital Twin gate access and shape the session.
Master switch for the entire Digital Twin. When off, the microphone affordance is hidden from every user. Default: off.
When on, only Admin users see Convo Mode. Useful while you’re testing a new provider, tuning voices, or troubleshooting an avatar setup before exposing it to learners. Default: on — flip to off once you’re ready for everyone.
Lets users type into the Convo Mode panel as well as speak. Helpful for noisy environments or accessibility.
Renders the live STT transcript inside the Convo Mode widget so users can see what was heard.
Launches the voice conversation automatically after sign-in: new visitors land in the immersive voice view (with a tap-to-start step) every time they sign in, instead of the classic chat. Default: off.
Once a session reaches the full-screen avatar view, people stay there for the whole conversation — the collapse button and the Escape key are turned off, and ending the call is the only way out. Use this for kiosk screens and embedded experiences. Default: off.

​
Choosing a Provider

Pick a provider by setting the Realtime Model field on the Digital Twin. The model string determines which provider Pria routes to.

OpenAI Realtime

Lowest latency, broadest model coverage, built-in OpenAI voices. The default choice for most Digital Twins. Uses WebRTC.

ElevenLabs

Premium voices via the ElevenLabs ConvAI agent bridge. Use when voice quality is the priority and your agent is already configured in the ElevenLabs dashboard.

Gemini Live

Google’s audio-native session with thinking support. Uses WebSocket; 30 prebuilt voices.

xAI Realtime

Grok voice with five built-in voices (eve, ara, rex, sal, leo). Uses WebSocket.

Anam Avatar

Animated avatar driven by your selected LLM. Anam owns mic, STT, TTS, and video; Pria supplies the assistant turn text — so your prompts, RAG, and tools still run on Pria.

Cartesia Voice

Pria owns the microphone, transcription, and LLM turn; Cartesia provides fast, expressive TTS with a large voice library (including cloned voices). Uses WebSocket.

​
Per-Provider Configuration

OpenAI API key resolves in this order: per-model key in Custom Models → Digital Twin’s openai_api_key → platform fallback.
ElevenLabs is the only provider where “agent” is a vendor-side concept — your ElevenLabs agent does the talking. Configure it to call Pria back as a Custom LLM if you want Pria’s prompts, RAG, and tools in the loop.
Gemini sessions are capped around 10 minutes per connection by Google; Pria configures a sliding context window so longer conversations keep working across reconnects.
Note: image markdown is sometimes garbled in spoken output on grok-fast — this is a current model limitation on xAI’s side.
Pria runs the LLM, RAG, tools, and personalization for every turn — Anam just renders the avatar and handles mic/TTS.
Pria owns the microphone, transcription, LLM turn, RAG, and tools — Cartesia only speaks the response, so everything your Digital Twin can do in chat works in voice too.

​
Voice Activity Detection (VAD)

VAD is how the provider decides when a user has finished speaking. Two knobs apply to OpenAI Realtime:
  • VAD Eagerness — low keeps the user talking longer between turns (good for thoughtful conversations); high cuts in faster (good for quick Q&A drills).
  • Noise Reduction — near_field cleans up headset audio; far_field cleans up laptop mics in rooms with background noise. Leave blank if your users are on quality hardware.
Gemini, xAI, ElevenLabs, Anam, and Cartesia manage VAD internally — those toggles are OpenAI-only.

​
Transcription Language

If your users speak a single non-English language, set the Transcription Language field (e.g. fr, es, de, ja). It biases the STT engine and reduces transcription errors. Leave blank for English or multilingual rooms. This setting applies to OpenAI Realtime only.

​
Tools During Voice Sessions

Anam and Cartesia sessions run every turn through Pria, so your Digital Twin’s tools — including image generation — work mid-conversation with no separate toggle. OpenAI Realtime sessions also carry the full Pria tool surface.

​
Testing Your Setup

1

Keep Convo Mode admin-only while testing

Leave Admin-only on while you tune voice, VAD, and avatar settings. You’ll be the only one who sees the microphone affordance.
2

Open Convo Mode

Sign in as an Admin user, open any conversation, and start a Convo Mode session.
3

Verify the basics

Confirm: the avatar (if any) appears, your voice is transcribed, the assistant responds in the chosen voice, and your assistant’s tools still fire mid-conversation.
4

Tune VAD if needed

If the assistant interrupts users mid-thought, drop VAD Eagerness to low. If responses feel sluggish, bump it to high.
5

Flip Admin-only off

Once you’re satisfied, turn off Admin-only so every user can use Convo Mode.

​
Cost Considerations

Convo Mode is billed per minute by every provider. Costs vary widely:
  • OpenAI Realtime and Gemini Live are billed on input/output audio tokens per minute by the provider.
  • ElevenLabs charges per character of TTS output plus session minutes.
  • xAI Realtime is billed on audio minutes.
  • Cartesia charges for TTS output on top of the underlying LLM cost.
  • Anam adds an avatar surcharge on top of the underlying LLM cost.
If you bring your own provider API keys via the Custom Models flow, those minutes are billed directly to your provider account. Otherwise they go through Pria’s platform billing.
The Anam avatar is the most expensive option per minute. If cost is a concern and you don’t need a visible persona, OpenAI Realtime or Gemini Live with a quality voice will deliver excellent results at a fraction of the cost.