---
title: "Real-time AI avatar APIs compared: LiveAvatar, Tavus, Simli, Anam, and D-ID"
description: "LiveAvatar, Tavus, Simli, Anam, and D-ID compared: what each API renders, what you bring, vendor latency claims, and current pricing. Reviewed November 2026."
url: "https://www.pixeltable.com/learn/real-time-ai-avatar-apis-compared"
updated: "2026-11-02"
vertical: "Agents"
doc: "https://docs.pixeltable.com/howto/cookbooks/agents/pattern-agent-memory"
---

# Real-time AI avatar APIs compared: LiveAvatar, Tavus, Simli, Anam, and D-ID

A real-time AI avatar API streams a talking face that answers a user live, usually over WebRTC. Under the face sits a voice agent: speech-to-text, a language model, text-to-speech, and turn-taking. The APIs differ in how much of that stack they run for you. Some run the whole conversation. Others take your agent's audio and return video frames.

Updated: 2026-11-02
Part of [What is agent memory?](https://www.pixeltable.com/learn/what-is-agent-memory).

## On this page

- [Two kinds of avatar API](https://www.pixeltable.com/learn/real-time-ai-avatar-apis-compared#what-it-is)
- [LiveAvatar (HeyGen)](https://www.pixeltable.com/learn/real-time-ai-avatar-apis-compared#liveavatar)
- [Tavus Conversational Video Interface](https://www.pixeltable.com/learn/real-time-ai-avatar-apis-compared#tavus)
- [Simli](https://www.pixeltable.com/learn/real-time-ai-avatar-apis-compared#simli)
- [Anam](https://www.pixeltable.com/learn/real-time-ai-avatar-apis-compared#anam)
- [D-ID](https://www.pixeltable.com/learn/real-time-ai-avatar-apis-compared#did)
- [How to choose](https://www.pixeltable.com/learn/real-time-ai-avatar-apis-compared#how-to-choose)
- [Last reviewed](https://www.pixeltable.com/learn/real-time-ai-avatar-apis-compared#review)
- [Comparison](https://www.pixeltable.com/learn/real-time-ai-avatar-apis-compared#comparison)
- [Where Pixeltable fits](https://www.pixeltable.com/learn/real-time-ai-avatar-apis-compared#where-pixeltable-fits)
- [Questions](https://www.pixeltable.com/learn/real-time-ai-avatar-apis-compared#questions)

## Two kinds of avatar API {#what-it-is}

Batch APIs render a finished video from a script or an audio file. You wait seconds to minutes and get an MP4. HeyGen video API and Hedra Character-3 work this way. HeyGen switched that video API to pay-as-you-go credits in late October 2026; this page does not quote those rates.
Real-time APIs hold a live session. The user speaks, the agent answers, and the face moves while the answer plays. Latency decides whether the conversation feels natural, so vendors publish latency figures. The figures below are each vendor's own claims. Nobody has run them side by side on this page.

## LiveAvatar (HeyGen) {#liveavatar}

LiveAvatar is HeyGen's real-time product, formerly Interactive Avatar. In Full mode it runs the voice, the language model, and the face. In Lite mode (Avatar Only on the LiveAvatar site) you bring your own LLM and voice and pay half the credits. HeyGen says the median time to first frame is under 300 ms. Plans start with 10 free credits; paid Essential and Business tiers add 1,100 and 6,000 credits. Full mode uses 2 credits per minute and Lite uses 1. See https://www.liveavatar.com and https://docs.liveavatar.com/docs/faq/credits for current rates. Sources: https://www.liveavatar.com , https://docs.liveavatar.com/docs/faq/credits , https://help.heygen.com/en/articles/12758516

## Tavus Conversational Video Interface {#tavus}

Tavus CVI runs the full pipeline: perception (Raven), turn-taking (Sparrow), speech-to-text, an LLM you can replace, text-to-speech, and the Phoenix face model. Sessions run over WebRTC through Daily. Tavus says Phoenix-4.5 turns audio into video in 134 ms. It does not publish a single full-pipeline millisecond figure on the CVI or pricing pages reviewed for this article. The public pricing page lists two developer ladders at once (November 2026): Basic, Starter, and Growth at 25, 100, and 1,250 conversational minutes with overage on paid tiers, and Free, Starter, Builder, Growth, and Business at 20, 60, 175, 1,300, and 4,000 minutes. Use https://www.tavus.io/pricing rather than a copied table. Tavus lists SOC 2, HIPAA, GDPR, and the EU AI Act. Sources: https://www.tavus.io/cvi , https://docs.tavus.io , https://www.tavus.io/pricing

## Simli {#simli}

Simli renders the face only. You run the voice agent (often with LiveKit or Pipecat), send Simli the agent audio, and get video back. Simli says audio-to-video takes about 150 ms. Pricing is per minute on Hobby (1,000 minutes), Pro, Scale (27,500 minutes), and enterprise tiers, with 50 free minutes a month. See https://www.simli.com/pricing for current rates. Sources: https://www.simli.com , https://www.simli.com/pricing , https://docs.simli.com

## Anam {#anam}

Anam runs the face and can run the conversation, and it accepts your own LLM. It lists integrations with LiveKit, Agora, and ElevenLabs, over 70 languages, and SOC 2 Type II. Anam published its own benchmark in October 2026 with a 1.24 s median reply time for the full pipeline. Plans run from 30 free minutes through named Starter, Explorer (250 minutes), and Professional (8,000 minutes) tiers. See https://anam.ai/pricing for current rates. Sources: https://anam.ai/pricing , https://anam.ai/api , https://anam.ai/tools/latency-benchmark

## D-ID {#did}

D-ID V4 Expressive Visual Agents answer from documents you upload (retrieval over your files) and stream over WebRTC. D-ID's tech specs say conversational latency is under 500 ms. Studio and API plan prices move, so use https://www.d-id.com/pricing rather than a copied table. Sources: https://www.d-id.com/v4-expressive-visual-avatars-tech-specs/ , https://www.d-id.com/news/v4-expressive-visual-agents-real-time-llm-connected-interaction/ , https://docs.d-id.com

## How to choose {#how-to-choose}

Pick from what you already run.
Whichever API renders the face, your app still owns the session records, transcripts, recordings, and anything the avatar should remember next time. None of these vendors is a database for that data.

- If you have no voice agent yet and want one vendor, start with LiveAvatar Full mode or Tavus CVI.
- If you already run a LiveKit or Pipecat agent, a face-only renderer such as Simli, or LiveAvatar Lite, keeps your LLM and voice choices.
- If the avatar answers from a document set and you want that hosted, D-ID agents include retrieval.
- If you need many languages or SOC 2 Type II paperwork, check Anam and Tavus first.
- If you only need pre-rendered clips, a batch API (HeyGen video API, Hedra Character-3) is usually cheaper per finished second than holding a live session. Check current batch rates; HeyGen API credits changed in late October 2026.

## Last reviewed {#review}

Facts on this page were checked against vendor documentation on 2026-11-02. Product surfaces move; treat version names and APIs as directional and follow the official links in Related.

## Real-time AI avatar APIs (last reviewed: Nov 2026) {#comparison}

|  | LiveAvatar | Tavus CVI | Simli | Anam | D-ID V4 agents |
| --- | --- | --- | --- | --- | --- |
| What it runs | Face, voice, LLM (Full); face only with your LLM and voice (Lite / Avatar Only) | Full pipeline, LLM replaceable | Face only | Face, plus conversation if you want it | Face, voice, LLM, retrieval over your docs |
| Transport | WebRTC | WebRTC via Daily | WebRTC; LiveKit plugin | WebRTC; LiveKit, Agora | WebRTC |
| Latency (vendor claim) | Under 300 ms median to first frame | 134 ms audio to video (Phoenix-4.5) | About 150 ms audio to video | 1.24 s median full reply (own Oct 2026 benchmark) | Under 500 ms conversational |
| Entry paid plan | Essential (1,100 credits); Business (6,000 credits) | See tavus.io/pricing (two developer ladders) | Hobby (1,000 min); Scale (27,500 min) | Starter; Explorer (250 min); Professional (8,000 min) | See d-id.com/pricing |
| Free tier | 10 credits | See tavus.io/pricing | 50 min a month | 30 min | Check d-id.com/pricing |

## Where Pixeltable fits {#where-pixeltable-fits}

Use Pixeltable when transcripts, session recordings, generated clips, and per-user memory should live in tables you query, with embeddings kept in sync as rows arrive. Pixeltable does not render faces. Keep the avatar API you chose and post each finished turn to a table. The table embeds it, and a query route returns what this user said in earlier sessions so your agent can put it in the prompt.

```python
import pixeltable as pxt
import pixeltable.functions as pxtf
from pixeltable.functions import openai
from pixeltable.serving import FastAPIRouter

TableModel = pxt.model_base()
embed = openai.embeddings.using(model='text-embedding-3-small')


class Turns(TableModel, name='turns'):
    id = pxt.Column(value=pxtf.uuid.uuid7(), primary_key=True)
    user_id: pxt.String
    session_id: pxt.String
    speaker: pxt.String  # 'user' or 'avatar'
    text: pxt.String

    __indexes__ = [pxt.EmbeddingIndex(text, embedding=embed), pxt.BtreeIndex(user_id)]


@pxt.query
def recall(user_id: str, query: str):
    sim = Turns.text.similarity(string=query)
    return (
        Turns.where(Turns.user_id == user_id)
        .order_by(sim, asc=False)
        .limit(5)
        .select(Turns.session_id, Turns.speaker, Turns.text)
    )


api = FastAPIRouter(name='avatar')
api.add_insert_route(Turns, path='/turns', inputs=[Turns.user_id, Turns.session_id, Turns.speaker, Turns.text], outputs=[Turns.id])
api.add_query_route(path='/memory', query=recall)
```

## Questions {#questions}

### Which real-time avatar API has the lowest latency? {#faq-1}

Each vendor publishes its own number and measures it differently: time to first frame, audio-to-video, or a full spoken reply. Compare them in your own region with your own agent before you pick.

### Can I use my own LLM? {#faq-2}

Yes with LiveAvatar Lite (Avatar Only), Tavus, Simli (you run the agent), and Anam. D-ID agents include retrieval over your documents and list external LLM support; check their current docs.

### Is HeyGen the same as LiveAvatar? {#faq-3}

LiveAvatar is HeyGen's real-time product. HeyGen's main API renders videos in batch, and that API moved to pay-as-you-go credits in late October 2026.

### Where do I store transcripts and memory for an avatar app? {#faq-4}

In your own database. Post each turn from your agent to a table with an embedding index and query it at the start of the next session. Pixeltable is one place to put that table. The give an AI avatar memory guide shows a full example.

## Related

- [How do I give a real-time AI avatar memory of past conversations?](https://www.pixeltable.com/learn/how-to/give-an-ai-avatar-memory)
- [How do I turn a script into a talking-head video with an API?](https://www.pixeltable.com/learn/how-to/build-a-talking-head-video-pipeline)
- [Mem0 vs Letta vs Zep](https://www.pixeltable.com/learn/mem0-vs-letta-vs-zep)
- [AI agents and MCP](https://www.pixeltable.com/use-cases/ai-agents-mcp)
- [Build an agent with memory](https://docs.pixeltable.com/howto/cookbooks/agents/pattern-agent-memory)
- [LiveAvatar](https://www.liveavatar.com)
- [Tavus pricing](https://www.tavus.io/pricing)
- [Simli pricing](https://www.simli.com/pricing)
- [Anam pricing](https://anam.ai/pricing)
- [D-ID pricing](https://www.d-id.com/pricing)