Skip to main content

heygen/avatar-6/talking-avatar

HeyGen Avatar 6 API animates a portrait photo and speech audio into a native 1080p or 2K talking video with script-aware hand gestures and direct motion direction.

From $0.12/s

Workbench

Input

Talking avatar
153/1200
HeyGen Avatar 6: optional plain-text motion and gesture direction (up to 1,200 chars). at least 1 characters · at most 1200 characters
1/1

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

  • 1
1 / 1 files
HeyGen Avatar 6: portrait photo or illustration (up to 32 MB). at least 1 characters
1/1
1 / 1 files
HeyGen Avatar 6: speech audio driving lip sync and clip length. at least 1 characters
affects price
HeyGen Avatar 6: 1080p or 2k output tier (changes per-second rate).
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?

FLAGSHIP 2K TALKING AVATAR API

HeyGen Avatar 6 API at a glance

HeyGen's highest-fidelity digital presenter model with context-matched gestures and native 2K clarity.

Up to 2K output
2K
Choose 1080p or 2K portrait and landscape video.
Audio duration
10 MIN
Accepts spoken audio tracks up to 10 minutes.
Expressiveness
2 MODES
Switch between default and less for facial motion intensity.

Results

What you can make with HeyGen Avatar 6

  • 1080P INTIMATE STUDIO DELIVERY

    Hushed eye contact with unhurried micro-expressions

    In the champagne satin studio sample at 1080p, warm amber studio light rests across the bare shoulder while the speaker delivers a soft, close-range line. Natural script-aware movement pairs subtle head tilts with a slow, confident smile rather than stiff repeated head loops. Supply a clean front-facing portrait and concise motion wording when an intimate late-night cadence matters.

    1080p studio whisper sample: a woman in a champagne satin gown slipping off one shoulder speaks softly to camera with lingering eye contact, gentle head tilts, and a confident slow smile.

  • NATIVE 2K EVENING CLARITY

    Crisp fabric and facial detail at 1620px short edge

    Rendered at 2K on a candlelit night balcony, the dark velvet off-shoulder sample holds soft highlights across skin and evening fabric through a calm spoken monologue. Selecting 2k expands the output short edge to 1620 pixels, suited to close-up portraits and large displays. Pairing steady warm lighting in image_url with gentle posture cues keeps blinks and transitions smooth.

    2K candlelit balcony sample: a woman in a dark velvet off-shoulder dress delivers a calm evening monologue with natural blinks and unhurried posture shifts in warm night light.

  • CONTEXT-MATCHED PERFORMANCE

    Prompt direction, expressiveness, and motion reference

    HeyGen says Avatar 6 examines roughly 30 seconds of surrounding speech context so posture shifts and hand gestures align with phrasing. Guide mood or gaze with up to 1,200 characters in prompt, switch expressiveness to less for calmer delivery, or attach one MP4 or WebM clip through reference_video_urls for animated or illustrated character motion.

Before you run it

What to know before you run HeyGen Avatar 6

Talking avatar
Video duration follows the uploaded speech audio; photo references work immediately, while realistic video references require dedicated consent.

Use cases

What to build with the HeyGen Avatar 6 API

  • Close-up brand and executive films

    Pair a single studio headshot with recorded narration at 2K (1620px short edge) to produce crisp founder updates or product launches without booking a camera crew.

  • Intimate late-night character monologues

    Combine atmospheric adult portraits—like our off-shoulder champagne satin studio clip or candlelit velvet balcony sample—with hushed voiceovers for dramatic previews and narrative vignettes.

  • Long-form lessons and studio briefings

    Drive continuous talking-head segments up to 10 minutes from a single audio track, relying on phrase-aware posture and gesture timing instead of short repetitive loops.

  • Portrait and widescreen custom layouts

    Keep the uploaded portrait proportions—as in our verified 1088×1632 vertical test—or specify exact even width and height pairs from 256 to 3840 pixels for fixed editorial slots.

  • Animated and illustrated character clips

    Attach a 2-second or longer MP4 or WebM motion clip in reference_video_urls on standard workspaces to guide rhythmic cadence for illustrated or animated speakers.

Prompts

HeyGen Avatar 6 prompt examples you can copy

  • Talking avatar

    Champagne satin studio whisper

    Result from this prompt

    She leans in closer with heavy-lidded eye contact, whispering intimately with a slow teasing tilt of her head, parted lips, and a lingering sultry smile.

    Why it works. Matches the 1080p studio whisper sample featuring an adult woman in a champagne satin gown slipping off one shoulder under warm studio light. Concise delivery cues let the quiet recording drive mouth timing while maintaining lingering eye contact.

    Try this prompt
  • Talking avatar

    Candlelit balcony evening monologue

    Result from this prompt

    She delivers an intimate late-night balcony whisper with slow blinks, a subtle shift of her bare shoulder, and a warm knowing smirk straight into the lens.

    Why it works. Matches the 2K dark velvet off-shoulder balcony sample. Keeping motion instructions understated complements candlelight highlights and crisp 1620px facial texture.

    Try this prompt
  • Talking avatar

    Late-night amber lounge murmur

    For a portrait of a woman in her late thirties in a low-cut emerald silk dress seated in a dimly lit velvet bar booth: she leans subtly forward, speaking in a quiet late-night cadence with lingering eye contact and a slow, knowing half-smile.

    Why it works. Built for a moody low-light bar portrait framed in warm amber shadows. Set expressiveness to default so delicate eyebrow lifts and shoulder turns follow natural pauses in a hushed audio track.

    Try this prompt
  • Talking avatar

    Midnight city window invitation

    For a close-up portrait of a woman in her mid-thirties wearing a black silk robe loosely draped off one bare shoulder beside a warmly lit hotel window: she speaks softly, glances down for a beat, and returns to the lens with an unhurried smile.

    Why it works. Uses a deliberate gaze beat to create quiet cinematic tension across a 10-to-20 second line. Establish the silk robe and warm window glow in the source portrait so the motion cue stays focused on pacing and eye line.

    Try this prompt
  • Talking avatar

    After-hours open-collar reflection

    For a portrait of a man in his early forties in an unbuttoned dark linen shirt under warm pendant bar lamps: he speaks in a low, unhurried voice with relaxed nods and a warm private smile at the close of each thought.

    Why it works. Shows how restrained adult framing and an open-collar evening look pair cleanly with calm spoken reflections. Switch expressiveness to less if you want a still posture throughout.

    Try this prompt
  • Talking avatar

    Candlelit vinyl lounge story

    For a portrait of a woman in her forties wearing a dark satin slip dress beneath a draped cashmere wrap in a candlelit listening room: she delivers her midnight story slowly with soft breaths, small chin tilts, and attentive gaze.

    Why it works. Tailored for 2K close-up narration lasting 30 to 60 seconds where subtle breathing and steady gaze carry the scene. Record speech close to the mic so quiet consonants register cleanly.

    Try this prompt

Pricing

HeyGen Avatar 6 API pricing

A 5-second clip starts at $0.6 at 1080p and $0.87 at 2K.

Get started

How to use the HeyGen Avatar 6 API in three steps

  1. Step 1

    Choose an authorized portrait

    Upload a clear JPEG, PNG, or WebP portrait (up to 32 MB) of a consenting adult you have permission to depict. Frame lighting, wardrobe, and setting in the source image.

  2. Step 2

    Prepare clean spoken audio

    Provide an MP3 or WAV recording between 1 and 600 seconds in audio_url. Review pacing and pauses beforehand, because whole input audio seconds set the charge.

  3. Step 3

    Set resolution and motion cues

    Pick 1080p or 2k, optionally add a plain-text prompt up to 1,200 characters, and keep expressiveness at default or set less for quieter delivery.

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

FAQ

HeyGen Avatar 6 API FAQ

About HeyGen Avatar 6

Build 1080p or 2K talking-avatar clips from an authorized adult portrait and clean speech track with HeyGen Avatar 6. Review the champagne satin studio whisper at 1080p and the candlelit velvet balcony monologue at 2K to judge lip sync, lingering gaze, and fine texture before scaling to longer narrations up to 10 minutes. Billing follows rounded-up input audio seconds at $0.12/s for 1080p or $0.174/s for 2K, with zero charge on failed runs.

Related models and next tasks