Skip to main content

heygen/avatar-iv/talking-avatar

HeyGen’s Avatar IV turns a front-facing portrait and up to 10 minutes of your own audio into a talking video, with prompt-guided gestures, three expression levels, an optional background image and output from 360p to 1080p.

From $0.054/s

Workbench

Input

Talking avatar
89/5000
Optional direction for expressions and gestures; this text does not set the audio-second billing rate. at least 1 characters · at most 5000 characters
1/1

Drop files or media links, paste, or browse · 1 file · Max 10 MB · JPG · PNG · WEBP

  • 1
1 / 1 files
Required clear, front-facing portrait of the speaker to animate; HeyGen billing follows the audio length rather than the portrait. at least 1 characters
1/1
1 / 1 files
Required speech recording, up to 10 minutes long; its duration sets the charge, rounded up to a whole second. at least 1 characters
0/1

Drop files or media links, paste, or browse · 1 file · Max 10 MB · JPG · PNG · WEBP

0 / 1 files
Optional image for a replacement setting behind the speaker; the billing basis remains the supplied audio duration. at least 1 characters
Expressiveness
lowmediumhigh
Movement intensity: low, medium, or high, default low; changing this setting does not affect the HeyGen rate.
Choose 16:9, 9:16, 1:1, 5:4, or 4:5; leave empty to follow the portrait, with billing still determined by audio seconds.
Five output tiers from 360p through 1080p; every resolution tier has the same HeyGen price.
Safety checkerOff

SpicyAPI does not run a safety checker on this model. Your prompt and media go to the model as written, and the model itself decides what comes back.

Checking your account before enabling submission and pricing.

Output

Ready for a new run
Example result

Missing the model you need?

PORTRAIT ANIMATION WITH BACKGROUND CONTROL

HeyGen Avatar IV API at a glance

Keep the speaker in the photo, supply the spoken recording, and choose a new background or a different expression level.

Speech limit
10 MIN
HeyGen accepts a speech recording up to 10 minutes long.
Resolution choices
5 TIERS
Five output tiers span 360p through 1080p without changing the rate.
Expression setting
3 LEVELS
Choose low, medium, or high; low is the default and all three cost the same.
Background image
SWAP
An optional background image places the speaker in another setting.
Frame proportions
5 RATIOS
Choose 16:9, 9:16, 1:1, 5:4, or 4:5, or leave the ratio empty to follow the photo.

Results

What you can make with HeyGen Avatar IV

  • SOFT DELIVERY, HIGH EXPRESSIVENESS

    A bedside portrait speaks the recorded line

    Our silk-robe example pairs a portrait on a bed with a short late-night recording. At 720p and high expressiveness, the woman speaks with a playful smile and lip sync that matches the audio. The prompt asks for soft delivery, small head tilts, and a glance; the recorded observation confirms the smile and speech synchronization, without establishing that every requested gesture appeared.

    Our 720p example at high expressiveness: the portrait speaks a short late-night line with a playful smile and lip sync matching the supplied audio.

  • A CRAFT EXPLANATION FROM A PHOTO

    The potter speaks at her wheel

    A portrait and a 10-second explanation produced a talking pottery clip with matched lip movement. The measured frame was 720×900 pixels. Use this example to plan a short workshop introduction: prepare the photographed setting and spoken recording, then add a concise delivery cue if needed. The result demonstrates a narrated portrait rather than a newly filmed pottery process.

    Our pottery test: about 10 seconds of synchronized speech in a 720×900 video.

  • BACKGROUND AND EXPRESSION CONTROLS

    The astronomer changes surroundings

    In the background test, an astronomer portrait appeared in front of the supplied greenhouse image. High expressiveness gave the speaker livelier movement. These are separate controls: background_image_url supplies the new setting, while expressiveness adjusts facial and head motion. Choose them according to the presentation you need and review the finished clip against both inputs.

    Our background-replacement test moved the rooftop speaker into a greenhouse with high expressiveness.

Before you run it

What to know before you run HeyGen Avatar IV

Talking avatar
Use photos and voices you have the right to use, and do not impersonate anyone with HeyGen Avatar IV.
Talking avatar
Keep HeyGen speech recordings within the 10-minute maximum.
All modes
HeyGen generated files are kept for 14 days, then deleted.

Use cases

What to build with the HeyGen Avatar IV API

  • Recorded workshop introductions

    Pair an adult instructor portrait with a prepared explanation, following the pottery test that matched a 10-second recording. Use the clip to introduce a craft lesson while keeping the practical demonstration in separate footage.

  • Presenter messages in a new setting

    Supply a background image for a different presentation location. The astronomer-to-greenhouse test demonstrates this setting change alongside high expressiveness; review both the surroundings and the speaker in the returned clip.

  • Quiet character dialogue

    Combine an authorized adult portrait with a short, softly spoken recording and modest gesture cues. The silk-robe example shows a playful smile and matched lip sync at 720p with high expressiveness.

  • Delivery comparisons for an introduction

    Keep the portrait and recording fixed while comparing low, medium, and high expression settings. This gives you a way to judge facial and head movement for the intended message without a rate change between settings.

  • Talking portraits for different layouts

    Choose a vertical, square, or landscape ratio for the destination layout, or follow the source photo. All five resolution tiers use one rate, so select resolution for the planned use and inspect the delivered framing.

Prompts

HeyGen Avatar IV prompt examples you can copy

  • Talking avatar

    A quiet bedside line

    Result from this prompt

    She speaks softly with a playful smile, small head tilts, a slow glance down and back up.

    Why it works. A suggested variation on the silk-robe delivery cue. Choose a matching authorized portrait and recording; the observed sample confirms the smile and lip sync, rather than every gesture in this direction.

    Try this prompt
  • Talking avatar

    A welcoming pottery instructor

    Result from this prompt

    She explains her craft with calm, friendly gestures.

    Why it works. The photo establishes the instructor, clothing, workshop, and light; this direction concentrates on a calm welcome. The pottery sample provides a reference for synchronized recorded explanation.

    Try this prompt
  • Talking avatar

    An enthusiastic science introduction

    The man in his forties in the supplied cardigan portrait speaks with an engaged expression, occasional light nods, and a warm smile as the recording reaches its closing phrase.

    Why it works. Add a greenhouse picture as the new background if you want the setting change from our test. This proposed delivery cue is separate from the background test and is not its measured input.

    Try this prompt
  • Talking avatar

    An evening host greeting

    For a portrait of a woman in her late thirties in a dark evening dress beside a warmly lit hotel window: she greets the camera with a composed smile, a gentle head tilt, and restrained gestures.

    Why it works. Prepare the evening wardrobe and window light in the source portrait. The prompt asks for a manner of speaking while an authorized recording carries the greeting.

    Try this prompt
  • Talking avatar

    A relaxed balcony invitation

    The man in his early forties in the open-collar linen shirt portrait speaks with an easy half smile and small nods, maintaining a relaxed mood in the soft dusk light.

    Why it works. An adult portrait supplies the shirt and lighting. To place the speaker in front of a balcony, use a separate background image rather than treating motion wording as a setting control.

    Try this prompt
  • Talking avatar

    A measured gallery introduction

    The curator in her fifties, photographed in a tailored jacket in a softly lit gallery, delivers the recording with a thoughtful expression, steady attention toward the camera, and a small smile at the end.

    Why it works. This direction gives the optional prompt a clear performance role. Try the low default before comparing a higher expression setting with the same portrait and speech.

    Try this prompt

Pricing

HeyGen Avatar IV API pricing

A 5-second clip starts at $0.27.

Get started

How to use the HeyGen Avatar IV API in three steps

  1. Step 1

    Prepare an authorized portrait

    Choose a clear, front-facing photo of an adult and a voice recording you have the right to use. Check that the planned clip does not impersonate anyone.

  2. Step 2

    Listen to the complete recording

    Supply the speech through audio_url and keep it within 10 minutes. Review the words, pacing, and duration before paying for a video based on that audio.

  3. Step 3

    Direct the motion and setting

    Add a brief expression or gesture prompt, then select low, medium, or high expressiveness. Provide background_image_url when you want the speaker in front of a different setting.

Parameter reference and code samples are in the API and Readme tabs at the top of this page.

FAQ

HeyGen Avatar IV API FAQ

About HeyGen Avatar IV

Build a HeyGen Avatar IV clip around a portrait and recording you are entitled to use. The pottery sample shows a short explanation with matched lip movement; the greenhouse sample adds a replacement setting, and the silk-robe clip demonstrates a softer delivery at high expressiveness. Treat these as concrete examples when choosing your own direction. Set the frame for where the video will appear, review the returned performance, and download it within 14 days. Audio seconds determine billing, while the five resolution tiers and three expression settings share the same rate.

Related models and next tasks