HeyGen Avatar V Presenter: 4K Specs & $0.10/sec
The short answer
HeyGen Avatar V Presenter, a digital twin video model that turns text or audio into lip-synced presenter video, is now callable through a model API and runs in the AdGraam Playground. It outputs 720p, 1080p or 4K as MP4 or WebM and costs $0.10 per second of script or audio in the Playground.
On this page (10 sections)
What is HeyGen Avatar V Presenter?
HeyGen Avatar V Presenter is a video model from HeyGen that creates digital twin presenter videos from text or audio, with lip-sync, optional backgrounds and captions. It is now callable through a model API and runs in the AdGraam Playground.
Avatar V sits in HeyGen's avatar line, alongside Avatar IV and III. HeyGen's own comparison page describes avatar models as the layer that delivers a script through a consistent person, as opposed to HeyGen Video, which generates scenes without a presenter.
An Instagram summary of HeyGen pricing says Avatar V learns your face, expressions and gestures from one 15-second clip. That is a secondary claim, not a HeyGen spec sheet.
HeyGen Avatar V Presenter release date and availability
HeyGen Avatar V Presenter appeared as callable on a model API on November 11, 2026, and is live in the AdGraam Playground. HeyGen has not published a dedicated launch note for this specific Presenter model that we can cite.
Avatar V itself predates this listing. Kling AI's October 27, 2026 review mentions it alongside Video Agent and the newer HeyGen Video model, which HeyGen introduced on October 21, 2026.
What is unclear: whether the API listing exposes every Avatar V capability, such as custom digital twin training. The listing describes text or audio input and preset voices.
HeyGen Avatar V Presenter key features and specs
The model takes a script or audio file and returns a lip-synced presenter video in 720p, 1080p or 4K. You can remove the background, add captions, and choose how the avatar fits the frame.
A control console with sliders and a waveform feeding a video frame
| Spec | Details |
|---|---|
| Model | HeyGen Avatar V · Presenter |
| Input | Text or audio |
| Resolution | 720p, 1080p, 4K |
| Output format | MP4, WebM |
| Fit | contain, cover |
| Remove background | Supported |
| Captions | Supported |
| Voices | Warm Pro Narrator, Chill Brian, Ivy, John Doe, Monika Sogam, Hope, Archer, Brittney |
| Max duration | Not announced |
| AdGraam Playground price | $0.10 per second of script or audio |
Background removal and WebM output are both listed, which may help if you want to place a presenter over product footage. The listing does not say whether WebM carries transparency, so check a test export first.
HeyGen Avatar V Presenter pricing and free access
In the AdGraam Playground, Avatar V Presenter costs $0.10 per second of your script or audio. A 30-second spot runs about $3.00, and a 60-second one about $6.00, before any retries.
HeyGen's own plans are separate. A Kling AI review, with prices checked October 22, 2026, lists:
| Plan | Monthly starting price | Conditions |
|---|---|---|
| Free | $0 | Up to 3 watermarked videos, 1 minute each |
| Creator | $29 | 600 credits, up to 1080p |
| Pro | From $49 | From 1,000 credits, up to 4K |
| Business | From $149 | 1,500 credits, extra seats $20 monthly |
Per-second billing is easier to forecast for testing hooks. A subscription may make more sense if your team works inside HeyGen's editor daily. See AdGraam pricing for credit packs.
HeyGen Avatar V vs HeyGen Video and Video Agent
HeyGen splits its stack into three tools. Avatar models deliver a script through a presenter, HeyGen Video generates 5 to 15 second scenes with native audio, and Video Agent assembles a finished multi-scene video from one prompt, per HeyGen's own comparison.
| Tool | Main input | Output | Presenter |
|---|---|---|---|
| HeyGen Avatar (V, IV, III) | Script or audio plus avatar | Up to 30 min | Yes |
| HeyGen Video | Prompt, image or references | 5 to 15 second clip | No |
| Video Agent | Prompt, script, URL or file | Multi-scene video | Yes |
Avatar V Presenter does one job: you supply the script or audio, and the same presenter delivers it each time.
Studio tools such as Creatify or Arcads are built around their own editors. This listing is a single model endpoint, so you would handle scripting, b-roll and testing around it. In AdGraam you can run it next to other models, rebuild competitor formats with Copy Ads and review Meta results. See AdGraam vs HeyGen and AdGraam vs Arcads.
How to use HeyGen Avatar V Presenter for ads
Avatar V Presenter fits ads where a consistent spokesperson carries the message: hooks, offer explainers, testimonial-style scripts and localized variants. It does not generate product scenes, so pair it with other models for b-roll.
A workbench with a phone, product box and storyboard cards laid out in sequence
A practical flow:
- Write 3 to 5 hook variants of 5 to 8 seconds each and render them at 720p to keep cost low at $0.10 per second.
- Use background removal to place the presenter over product shots or lifestyle footage.
- Turn on captions for sound-off feeds, then re-render winners at 1080p or 4K.
- Chain avatar, image and video steps in Flow Builder for repeatable batches.
Judge results with hook rate and hold rate benchmarks. For full UGC pipelines from a product URL, Video Agent is the closer match. For background reading, see the AI UGC ads guide.
What to watch next
HeyGen has not announced a maximum clip length, language list or custom twin support for this API listing. Until it does, it is unclear whether you can use it for localized campaigns in many markets.
Also watch how HeyGen positions Avatar V against its new HeyGen Video model, and whether the per-second rate holds as more providers list it. Reviewers cited on the Kling AI page flag inconsistent visual details, so run side-by-side tests before committing spend.
Key takeaways
- HeyGen Avatar V Presenter generates lip-synced digital twin video from text or audio.
- Output resolutions are 720p, 1080p and 4K, in MP4 or WebM.
- AdGraam Playground charges $0.10 per second of script or audio.
- Options include background removal, captions, and a contain or cover fit.
- Eight preset voices are listed, including Warm Pro Narrator, Chill Brian and Ivy.
- An Instagram summary says Avatar V learns a face, expressions and gestures from one 15-second clip.
Compare 200+ AI video and image models side by side
Run Kling, Veo, Sora, Seedance, Flux, Ideogram and Recraft in one Playground, or turn any product URL into ready-to-launch ads.
Frequently asked
What is HeyGen Avatar V Presenter?
It is a HeyGen video model that creates digital twin presenter videos from text or audio, with lip-sync, optional backgrounds and captions. It is part of the Avatar V family and is now callable through a model API.
How much does HeyGen Avatar V Presenter cost?
In the AdGraam Playground it costs $0.10 per second of your script or audio. HeyGen's own plans start with a free tier of 3 watermarked videos a month, per a Kling AI review that checked prices on October 22, 2026.
What resolutions does it support?
It supports 720p, 1080p and 4K. Output formats are MP4 and WebM.
How do I access HeyGen Avatar V Presenter?
You can run it in the AdGraam Playground, or reach it through API providers. HeyGen's own comparison pages also list Avatar V among its avatar models.
How does Avatar V differ from HeyGen Video?
Per HeyGen's own comparison, HeyGen Video makes 5 to 15 second scene clips with native audio and no presenter. Avatar models deliver a script through a consistent presenter, from 30 seconds up to 30 minutes.
Sources
- HeyGen Video vs Avatar vs Video Agent: Which to Use ...heygen.com
- HeyGen Reviews for Your Next Video Projectkling.ai
- HeyGen pricing in 30 seconds. Free is watermarked. Swipe ...instagram.com
- HeyGen vs Synthesia vs D-ID: AI Avatars Compared (2026)heygen.com
More AI model news & creative guides

Midjourney V8.2 Text to Image: API, Specs & Pricing
Midjourney V8.2 Text to Image is now callable on a model API: four images per prompt, native 2K HD. Get the spec table, ad workflow breakdown and access details.

FLUX 3 Image: Native 4K, Klein Open Weights & Price
FLUX 3 Image from Black Forest Labs: native 2K and 4K, bounding boxes, 10 references, $0.041 per image. Get the spec table, ad workflow and access details.

CapCut Web Ultra: 7 Days Unlimited Seedream Images
CapCut Web Ultra reportedly offers 7 days of unlimited Seedream 5.5 and GPT Image 2.5 generation for Nov 13-19 buyers. Get the spec table, ad workflow tips and access.
Best AI Ad Generators for D2C Brands in 2026
Ten AI ad generators compared for D2C and e-commerce brands: what each makes, real starting prices, free options, and which suits Indian brands paying in rupees.
Break Even ROAS for COD Orders: How RTO Changes the Math
How to work out break even ROAS when a share of COD orders comes back as RTO, with worked rupee examples, a prepaid and COD mix, and why Ads Manager ROAS overstates COD.
What Indian D2C Brands Run on Meta: 2,790 Ads Analyzed
We studied 2,790 Facebook and Instagram ads from 14 Indian brands and their 747 longest-running ads: formats, angles, offers, languages and CTAs that last.
Your move
See your product as a winning ad
Turn a product URL into static ads and UGC-style videos, rebuild the competitor ads that already work, and read your Meta data to know what to make next.
AdGraam News DeskAI video and image news
The AdGraam News Desk (part of AdGraam, also searched as Adgram or Adgram AI) tracks AI image and video model launches, leaks and rumors from labs, leakers and creators, and checks each claim against its sources. Unconfirmed stories say so, and each page is updated as its story develops.