Skip to main content
Anam adds a real-time animated avatar to Convo Mode. While the user speaks to the Digital Twin, an embodied character appears on screen with synchronised lipsync, expressions, and natural turn-taking. Your chosen conversation model still does the thinking — Anam handles voice synthesis, animation, and the audio plane.
Anam is the recommended avatar provider for new setups. LemonSlice is still supported for institutions that haven’t migrated yet, but new deployments should choose Anam.

​
What Anam Is

Anam is a vendor that streams a photorealistic animated avatar over WebRTC, with built-in microphone capture, speech recognition, voice synthesis, and lip-sync. Pria connects to Anam as a Custom LLM — meaning your Conversation model (any provider Pria supports) generates the assistant’s words, and Anam speaks them through the avatar. 
User speaks → Anam (mic, STT) → Pria (your LLM, RAG, tools) → text back →
                                                                   ↓
                                                         Anam (TTS + lipsync) → User sees and hears
This split lets you keep all the brain power inside Pria (knowledge base, IP Vault, tools, memory, guardrails) while outsourcing the voice + video presence to a vendor optimized for it.

​
When to Use Anam

High-engagement training

Onboarding, compliance modules, role-play scenarios where an embodied character holds attention better than a text bot.

Sales & marketing demos

Greeter avatars on landing pages, interactive product walkthroughs, video-call-style sales conversations.

Accessibility

Visible mouth movements support lip-reading and comprehension for users with hearing differences.

Classroom presence

A consistent visual tutor across sessions feels more like a teaching assistant than a chat interface.
For fast Q&A, code help, or text-heavy conversations, a plain voice provider (OpenAI Realtime, Gemini Live, ElevenLabs) is usually a better fit.

​
Prerequisites

Before configuring Anam in Pria, make sure you have:
  • An Anam account with API access — sign up at anam.ai
  • An Anam API key from your Anam dashboard
  • An Avatar ID for the character you want to display (browse the Anam avatar catalog in your dashboard)
  • A Voice ID that matches the persona you’re building
If you’d prefer not to manage Anam credentials yourself, the Praxis AI team can provision per-institution access. Contact humans@praxis-ai.com to request setup.

​
Setup Steps

1

Open Configuration

Navigate to Admin → select your Digital Twin → Configuration tab. Find the Anam section.
2

Paste your Anam API key

Paste the API key from your Anam dashboard into the Anam API Key field. This is stored encrypted server-side and never exposed to the browser.
3

Set the Avatar ID

Enter the UUID of the Anam avatar you want to use. Find this in your Anam dashboard alongside each avatar in the catalog.
4

Set the Voice ID

Enter the Voice ID from the Anam voice catalog. Match the voice to your avatar’s persona (tone, accent, age) for the most natural feel.
5

Add a Placeholder Image URL

Provide a still image URL that’s shown when the avatar is idle (before connecting and when paused). A clean headshot of the avatar works well.
6

Add a Loading Video URL

Provide a short looping video URL that plays while the session is connecting. This avoids dead time during the handshake.
7

Write an Intro Message

Type the opening line the avatar speaks when a user opens Convo Mode (e.g. “Hi! Ready to dive into today’s lesson?”). Keep it short and welcoming.
8

Pick a dedicated voice-turn model (optional)

Optionally set an Anam conversation model — a model used only for the avatar’s voice turns. Leave blank to inherit the Digital Twin’s normal conversation model. A faster model here keeps spoken replies snappy without changing the Twin’s text-chat behaviour.
9

Switch the voice provider in Personalization

Open the Personalization tab → Convo Mode section → set the voice provider to Anam. Save.

​
Connecting the LLM

Anam runs in Custom LLM mode — it does not have its own reasoning engine. Instead, each conversational turn flows like this:
  1. User speaks → Anam transcribes audio in the browser.
  2. Browser sends the user’s utterance to Pria.
  3. Pria runs your configured Conversation Model (any provider — Claude, GPT, Gemini, Grok, etc.) with full access to RAG, IP Vault, tools, and conversation history.
  4. Pria streams the assistant’s reply back to the browser.
  5. Anam speaks the reply through the avatar with synchronised lipsync.
This means you can change the conversation model independently of the avatar — switch to a faster model for snappy demos, or a larger model for deeper tutoring, without changing the avatar configuration.
The Conversation Model is configured per Digital Twin in the AI Models section. The avatar uses whatever you’ve selected there.

​
Testing the Avatar

1

Open Convo Mode

From any Digital Twin chat view, click the Convo button (the microphone icon in the input area).
2

Watch the loading video

The loading video should play for a second or two while the session connects.
3

Hear the intro message

The avatar should speak the intro message you configured. If you hear silence, double-check the Voice ID and Avatar ID.
4

Have a conversation

Speak naturally — the avatar should respond with synchronised lipsync. Tool calls (search, IP Vault lookups) happen invisibly server-side; the avatar just speaks the answer.

​
Per-Assistant Voice Model Override

The avatar and voice are configured once per Digital Twin, but each assistant can override the model used for its voice turns. In the assistant’s edit panel, set the voice conversation model — it applies only when that assistant runs in speech-to-speech mode (ElevenLabs, Anam, or LemonSlice). If unset, voice mode uses the assistant’s normal conversation model, then the Digital Twin’s voice/default model. This lets a “Sales Onboarding” assistant answer with a fast, snappy model while a “Research Tutor” assistant uses a deeper model — all through the same avatar.

​
Cost Notes

Anam bills per minute of active avatar time, separately from Pria credits. You’ll see usage in your Anam dashboard. Strategies to keep costs down:
  • Use Anam only for the Digital Twins where the avatar matters — sales, training, accessibility. Use plain voice (Gemini Live, OpenAI Realtime) for fast Q&A Twins.
  • Set a sensible intro message so users immediately know they’re in a voice/avatar session and aren’t surprised by the meter running.
  • Use a fast voice-turn model — a dedicated Anam conversation model keeps spoken turns short and inexpensive without changing text chat.
If you’re using Praxis-managed Anam credentials, billing is consolidated with your Praxis subscription — contact humans@praxis-ai.com for plan details.

​
Troubleshooting

  • Verify the Anam API Key is saved correctly in Configuration (no trailing spaces).
  • Confirm the Avatar ID exists in your Anam dashboard.
  • If you have an Anam account but no funds, the session will fail to mint — check your Anam billing status.
  • Usually a network jitter issue. Have the user try a wired connection or a less-congested Wi-Fi.
  • If persistent across all users, try a different Voice ID — some voices have tighter lipsync alignment than others.
  • Check that the user’s browser allows microphone access (browser permission, OS permission, headset selected).
  • On corporate networks, WebRTC traffic may be filtered. Test from a personal network to isolate.
  • The conversation model may be misconfigured. Check the AI Models tab and confirm a valid Conversation Model is selected.
  • Look at the chat history view after the session — if no assistant messages appear, the LLM is failing silently.
  • Confirm the browser allows video playback (autoplay policies can block the avatar stream).
  • Verify the placeholder image URL is publicly accessible (no auth, correct CORS).