Activating Conversation Mode
Locate convo mode icon
From the main interface, look for the Conversation icon on the text input bar
Voice Providers
Convo Mode supports three real-time voice providers. Your administrator selects which provider your Digital Twin uses.- OpenAI GPT-Realtime
- ElevenLabs
- Gemini Live
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
- Voice Activity Detection (VAD) — Configurable eagerness controls how quickly the AI responds when you pause speaking
- Tool calling — Your Digital Twin can access its full set of tools (search, file lookup, web browsing, etc.) during voice conversations
- MCP support — Connected MCP servers are available during real-time conversations
- Token tracking — Input and output token usage is tracked and displayed
Features
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.
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.
Audio Transcriptions
All voice conversations are automatically saved as searchable transcript
files that you can access, review, and reference at any time.
Display Modes
Convo Mode offers flexible layouts to fit your workflow:| Mode | Description |
|---|---|
| Normal | Compact floating panel — great for quick voice conversations alongside your chat |
| Expanded | Full-width panel — more room for the conversation transcript and controls |
Provider Comparison
| Feature | OpenAI GPT-Realtime | Gemini Live | ElevenLabs |
|---|---|---|---|
| Voice selection in Pria | Yes (10+ voices) | Yes (30 voices) | Configured in dashboard |
| VAD control | Adjustable eagerness | Automatic | Automatic |
| Tool calling | Full tool access | Full tool access | Dashboard-configured |
| MCP server support | Yes | No | No |
| Text input mode | Yes | Yes | Yes |
| Token tracking | Yes | Yes | No |
| Custom voice clones | No | No | Yes |
| Live transcription | Output only | Input and output | Output only |
| Proactive audio | No | Yes | No |
| Noise reduction | Configurable | Automatic | Automatic |
| Dynamic variables | N/A (full context in prompt) | N/A (full context in prompt) | Auto-injected |
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
Microphone not working
Microphone not working
Check permissions and hardware connections. Your microphone needs to be
enabled in the browser for Convo Mode to work.
Poor audio quality
Poor audio quality
Adjust input sensitivity and check for background noise.
Echo or feedback
Echo or feedback
Use headphones or adjust speaker volume.
Voice not recognized
Voice not recognized
Speak clearly and check language settings.
AI not responding
AI not responding
Check internet connection and try restarting the conversation.
Context lost
Context lost
Provide a brief recap of your previous discussion and pick up from there.
Misunderstood requests
Misunderstood requests
Rephrase using different words or examples.
Language switching problems
Language switching problems
Explicitly state language changes if the Digital Twin does not pick up on the switch.
Voice options not visible
Voice options not visible
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.
Related
- AI Models — Real-time speech-to-speech model options
- Configuration — Voice provider selection for administrators
- Input & Responses — Text and voice input options
- Gemini Live Integration — Admin setup guide for Gemini Live voice