# HeyGen

Canonical page: https://fuser.studio/models/heygen

HeyGen in Fuser animates a portrait photo into a talking presenter video at up to 1080p, driven by text or an audio track. Pair it with voice nodes.

## Specs

| Spec | Value |
| --- | --- |
| Inputs | Image, Audio, Prompt (text) |
| Output | video |
| Resolution | 360p, 480p, 540p, 720p, 1080p |
| Aspect ratios | 16:9, 9:16, 4:5, 5:4, 1:1 |
| Cost | 138–8,266 credits per run |

One portrait and one voice, and your presenter blinks, tilts and gestures in time with every line, no camera crew required

Creator: HeyGen

Also known as: Avatar IV, HeyGen Avatar 4

[Give it a voice](https://app.fuser.studio)

## How HeyGen works

Start with a still face, add either a voice recording or a script, and tune the delivery. Your audio sets the clip length, so a short test costs far less than a long render.

### Upload a sharp portrait

Drop in a front-facing, well-lit photo with eyes and mouth clearly visible and room above the head and shoulders.

### Bring audio or write a script

Connect a voice recording to drive the performance, or type the exact words and pick a voice from the library.

### Set the style and render

Choose aspect ratio, resolution, stable or expressive delivery and optional burned-in captions, then generate the clip.

## What HeyGen is good at

Performance is the point: expression that follows the voice, delivery you can dial from composed to animated, and a workflow built to iterate cheaply before a final render.

### Voice-driven micro-expressions

It reads tone, rhythm and emotion in the audio, then generates matching head movement, blinks, brow shifts and subtle hand gestures instead of simply mapping mouth shapes to syllables.

### Stable or expressive delivery

Stable keeps motion restrained for training and formal announcements. Expressive adds livelier brows and bigger gestures for marketing and social, across 16:9, 9:16, 4:5, 5:4, 1:1 or auto framing.

### Audio or script, your call

Upload a recorded track and it sets the video length and overrides prompt and voice. Or type a script and choose a voice such as Warm Pro Narrator, an excited UGC read or a serious broadcaster.

### 360p drafts, 1080p finals

Test a script cheaply at 360p to 540p, then render the final at 720p or 1080p. Optional burned-in captions keep muted social playback readable.

## Made with HeyGen

A gallery of presenters, from fashion editors and lighthouse keepers to vertical product reviewers and archival narrators, all speaking straight to camera in locked-off framing.

### Fashion editorial presenter

### Cinematic character monologue

### Vertical UGC product review

### Brand broadcast explainer

### Historical documentary narrative

## What people build with HeyGen

For marketers, mascot owners, trainers and storytellers who have a face and something to say and want a presenter without filming.

### Social ad hook spokespeople

Turn one headshot and an energetic read into a UGC-style hook in 9:16. Expressive style amplifies the energy of your audio, so punchy delivery lands with lively brows and gestures.

### Talking brand mascots

Give a stylised character or mascot illustration a voice. It handles characters and even animal photos, so your brand figure can greet, announce and sell to camera.

### Multilingual spokesperson clips

Bring your own recorded audio in another language and the same portrait delivers it with matching lip motion, so localized messages don't need a new shoot.

### Training and announcement presenters

Pick stable style and a serious or professional voice to produce composed presenters for onboarding, policy updates and internal announcements, without booking a studio.

### Documentary narrators from stills

Let an archival portrait or character study speak its own words. Locked-off framing and natural blinks suit interviews, history pieces and short film voiceovers.

## HeyGen questions, answered

### Is HeyGen the same as Avatar IV or HeyGen Avatar 4?

Yes, Avatar IV and Avatar 4 are the same HeyGen photo-to-talking-video model. It is HeyGen's photo-driven avatar engine, rolled out in mid-2025, and it turns a single still image into a lip-synced presenter with head movement, blinks, micro-expressions and subtle hand gestures.

### What do I need to make a talking video with HeyGen?

You need one portrait image and either an audio track or a text script. With audio, the recording drives the performance, sets the video length and overrides the prompt and voice. With text, you write the words to speak and pick a voice from the library.

### What's the difference between stable and expressive talking style?

Stable gives minimal, subtle motion suited to corporate, training and formal announcements, while expressive gives bigger gestures and facial energy for marketing and social. Expressive amplifies the audio's energy but can't create energy a flat voice lacks.

### What kind of photo works best?

A sharp, well-lit, front-facing portrait with the mouth and eyes clearly visible works best. Leave headroom and shoulder space so tilts and gestures aren't cropped. Sunglasses, hair over the face, hands near the mouth, harsh side-shadows and extreme profiles cause problems.

### Can it do camera moves, full-body action or multiple characters?

No, it is a performance tool, not a general video generator. The subject stays a talking presenter in a mostly static frame, so scenes needing camera movement, body action or physical interaction are better handled elsewhere. Long flat monologues also feel static without cutaways.

### How is a HeyGen video billed, and how can I keep the cost down?

It is billed per second of generated video, so cost scales with clip length and resolution. Revisions cost full price, so iterate with short scripts at 360p to 540p, then render the final at 720p or 1080p.

## Try HeyGen on Fuser

One portrait and one voice, and your presenter blinks, tilts and gestures in time with every line, no camera crew required

[Give it a voice](https://app.fuser.studio)

## Recipes using HeyGen

- [Translate to Voice Video (Male)](https://fuser.studio/recipes/translate-to-voice-video-male.md): Provide a scenario image, script, voice, and language to create a talking character video with translated speech.
- [Translate to Voice Video (Female)](https://fuser.studio/recipes/translate-to-voice-video-female.md): Turn a script, scenario image, voice selection, and target language into a talking character video.
- [Script to Voice Video (Male)](https://fuser.studio/recipes/script-to-voice-video-male.md): Provide a scenario image, script, and voice to create a talking character video with voiceover.
- [Script to Voice Video (Female)](https://fuser.studio/recipes/script-to-voice-video-female.md): Provide a scenario image, script, and voice selection to create a talking character video with spoken delivery.

## Used for

- [Brand identity & systems](https://fuser.studio/solutions/use-cases/brand-identity-systems.md): Explore a brand’s visual identity, refine typography and build real applications. Combine AI imagery with editable design and reusable workflows in Fuser.
- [Creative agencies](https://fuser.studio/solutions/industries/creative-agencies.md): Develop pitches, campaign assets and interactive client work in Fuser. Combine AI generation, editable design and reusable processes across your agency.
- [Film & animation](https://fuser.studio/solutions/industries/film-animation.md): Develop film treatments, character and environment concepts, storyboards and motion studies. Connect image, video and 3D exploration in Fuser.
- [Social content](https://fuser.studio/solutions/use-cases/social-content.md): Create social graphics, carousel artwork and short videos with a recognizable brand style. Keep copy editable and recurring content easier to produce in Fuser.
- [Video & storyboards](https://fuser.studio/solutions/use-cases/video-storyboards.md): Develop storyboard frames, shot variations and video studies from your references. Compose clear boards and explore movement in one Fuser project.

## Related models

- [Kling 3.0 Video](https://fuser.studio/models/kling-3-0-video.md)
- [MiniMax H3](https://fuser.studio/models/minimax-h3.md)
- [Seedance 2](https://fuser.studio/models/seedance-2.md)
- [Gemini Omni Video](https://fuser.studio/models/gemini-omni-video.md)
- [Grok Imagine](https://fuser.studio/models/grok-imagine.md)
- [Kling O3 Edit](https://fuser.studio/models/kling-o3-edit.md)

Node reference: [HeyGen docs](https://docs.fuser.studio/docs/nodes/video/heygen.md)

## More articles

- [Best AI Lip Sync Tools (2026): One Voice Line, Four Models](https://fuser.studio/articles/best-ai-lip-sync-tools.md)
- [Best AI Avatar Video Generators: One Portrait, One Script, Four Models](https://fuser.studio/articles/best-ai-avatar-video-generators.md)