← All video models

Hedra · AI avatar

Character-2

Hedra's proprietary controllable avatar generation model, supporting precise long-audio lip-sync and facial expressions, outputting video with audio.

Developer

Hedra

Type

AI avatar

Status

Active

Last confirmed

Sep 25, 2026

Next review Oct 25, 2026

Official specs

Official specs of Character-2
Clip length1–90 seconds
What it can doAI avatar, Lip sync
Highest resolution1080p
AudioGenerates its own audio

Hedra's proprietary Expressive Avatar model, driving lip-sync and facial micro-expressions with long audio, outputting video with audio.
From Hedra's own page, confirmed on Sep 25, 2026. This is what the model can do; whether a given channel sells it, and at which settings, is in the prices below. Official spec page

Where it is available

Where Character-2 is available
ToolTypeLowest monthly pricePrice status
HedraAvatars and Character Videos$10Price verified

"Lowest monthly price" is the cheapest confirmed monthly plan for that tool. It does not mean that plan includes this model — premium models are often limited to pricier plans. Each tool's official pricing page is the authority.

This model is included in plans on Hedra, but we found no exact official rate for it there, so no durations are listed — we don't estimate on a vendor's behalf.

How the status is checked

Whether a model still runs is checked separately from prices: prices change monthly, but a model can disappear between two price syncs, quietly making every page that mentions it wrong. So each model record has its own confirmation date and review deadline; overdue records are flagged, never assumed to still be running.

Last confirmed on Sep 25, 2026; due to be rechecked by Oct 25, 2026.

Recommended Alternatives & Budget-Friendly Picks

Based on the same model category (AI avatar), public specs, and availability across channels, here are recommended alternatives:

Avatar IV HeyGen
1080p With audio

HeyGen's AI avatar model, listed on its official pricing page. It does a different job from pure video generation models, so they are not compared.

Model Details