Avatar API latency
benchmark

Eighty people each held sixteen live, unscripted conversations across Anam Cara-4, HeyGen LiveAvatar, LemonSlice 2.1 and Tavus Phoenix-4, and rated what they experienced. 1,280 rated conversations. Every product ran its own default stack.

Measured July 31, 2026

Data from 80 participants

Includes 1,193 sessions

Benchmark snapshot

Median TTFF, default-stack study

Anam

1.550s

HeyGen

4.712s

Tavus

5.720s

🍋

LemonSlice

9.395s

Overview: Anam's 95th percentile, 3.6s, was quicker than every rival's median.

Overview: Anam's 95th percentile, 3.6s, was quicker than every rival's median.

Vendor

Median

P95

P99

n

1 Anam

1.550s

3.606s

8.290s

301

2 HeyGen

4.712s

8.692s

10.624s

300

3 Tavus

5.720s

8.092s

16.366s

304

4 LemonSlice

9.395s

15.130s

39.241s

288

For Anam and Tavus measured connection time included dynamically configuring the avatar used in the call. For HeyGen and Lemonslice, pre-configured avatars were used. Anam lets you configure your avatar at the same time as requesting your session token at no extra cost. For Tavus, this requires a separate API call which we measured independently at 1.4s. To ensure a fair comparison between the competitors we subtracted 1.4s from the measured connection times for Tavus.

Results: Anam connected fastest for every rater

Results: Anam connected fastest for every rater

Time to first frame

Time to first frame

July 31st, 2026

July 31st, 2026

Anam

Anam

median 1.6 s; n=301
median 1.6 s; n=301

HeyGen

HeyGen

median 4.7 s; n=300
median 4.7 s; n=300

Tavus

Tavus

median 5.7 s; n=304

LemonSlice

LemonSlice

median 9.4 s; n=288
median 9.4 s; n=288
Free AI Avatar Tools for Builders, Latency & API : AnamTTFF means time from pressing Start to the first visible avatar video frame, not conversational response latency. Illustrative distribution shapes are shown because raw sessions are unavailable; dashed markers and summary statistics are measured values. Anam: P95 3.606 s, P99 8.290 s, exact median 1.550 s, median 1.6 s · n=301. HeyGen: P95 8.692 s, P99 10.624 s, exact median 4.712 s, median 4.7 s · n=300. Tavus: P95 8.092 s, P99 16.366 s, exact median 5.720 s, median 5.7 s · n=304. LemonSlice: P95 15.130 s, P99 39.241 s, exact median 9.395 s, median 9.4 s · n=288.
0s
2s
4s
6s
8s
10s
12s

Time from pressing start to the first video frame, every rated session. Anam connected fastest for every rater; our 95th percentile, 3.6 s, is quicker than any rival's median.

Methodology: How TTFF was measured

Methodology: How TTFF was measured

TTFF is the time from pressing Start to first visible avatar video frame. The benchmark used 80 raters, 1,280 rated conversations, and provider default stacks.

Median TTFF

Typical wait before the avatar appears.

Default-stack realism

Provider production path, not a synthetic best case.

P95 / P99

How bad slow sessions get.

Sample size

How many measured sessions support the number.

Measured on 31 July 2026. These products change continuously and we make no claim about how any of them performs today, the method is published so the run can be repeated against whatever is being served now.

What is being measured?

What is being measured?

For Anam: Creating a persona (ephemeral), requesting a session token and connecting to the call

For Heygen: Requesting a session token and connecting to the call with a pre-defined persona

For Tavus: Creating a persona, creating the room, joining the room

🍋

For Lemonslice: Creating a room, joining the room with a pre-defined persona

Data and Transparency: Nothing to hide

Data and Transparency: Nothing to hide

Every rating, session telemetry, raw audio timing, provider configuration, harness code, and reproduction script is published.

At Anam we take take fairness and transparency seriously. We recognise that there is a conflict of interest inherent in running and publishing our own benchmark results. This is why we make all the code and data associated with the numbers we publish available so that anyone can check our work and reproduce it.

Build with the real-time avatar API behind the fastest benchmark result

Build with the real-time avatar API behind the fastest benchmark result

Production API for low-latency conversational avatars.

Production API for low-latency conversational avatars.