Hunyuan Avatar

Hunyuan Avatar

Playground

Hunyuan Avatar creates audio-driven talking or singing videos from one image + audio, in 480p/720p up to 120s (starts at $0.15/5s). Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Hunyuan Avatar is an advanced audio-driven avatar generation model that creates talking head videos from a single image and audio track. Upload a portrait and audio file, and the model generates a realistic video with synchronized lip movements, facial expressions, and natural head motion.

Why It Stands Out

• Audio-driven animation: Generates realistic talking head videos synced to any audio track.
• Single image input: Create animated avatars from just one portrait photo.
• Natural expressions: Produces lifelike facial movements, lip sync, and subtle head motion.
• Prompt support: Add optional prompts to guide style and expression. Use the Prompt Enhancer for optimization.
• Resolution options: Choose between 480p for faster processing or 720p for higher quality.
• Reproducibility: Use the seed parameter to recreate exact results.

Parameters

How to Use

1. Upload your audio — drag and drop a file or paste a public URL.
2. Upload a portrait image — provide a clear, front-facing photo.
3. Add a prompt (optional) — describe desired expressions or style. Use the Prompt Enhancer for AI-assisted optimization.
4. Select resolution — choose 480p for speed or 720p for quality.
5. Click Run and wait for processing.
6. Preview and download the animated avatar video.

Best Use Cases

• Virtual Presenters — Create AI spokespersons for videos and presentations.
• Content Creation — Generate talking head videos for social media and YouTube.
• E-learning — Produce instructor videos from static photos and voiceovers.
• Marketing & Advertising — Create personalized video messages at scale.
• Localization — Generate multilingual versions of spokesperson videos.
• Customer Service — Build animated avatars for video FAQs and support content.

Pricing

Total cost = (audio duration in seconds / 5) × price per 5 seconds

Billing Rules

• Minimum charge: 5 seconds
• Maximum billable duration: 120 seconds (2 minutes)

Examples (480p)

• 5s audio → $0.15 (minimum)
• 10s audio → $0.30
• 30s audio → $0.90
• 60s audio → $1.80
• 2 min (120s) audio → $3.60 (maximum)

Examples (720p)

• 5s audio → $0.30 (minimum)
• 10s audio → $0.60
• 30s audio → $1.80
• 60s audio → $3.60
• 2 min (120s) audio → $7.20 (maximum)

Pro Tips for Best Quality

• Use clear, front-facing portrait photos with good lighting.
• Ensure the face is centered and not obscured by hair or accessories.
• Use high-quality audio with clear speech for best lip sync.
• Choose 480p for drafts and quick iterations, 720p for final delivery.
• Neutral expressions in the source image allow for more natural animation.

Notes

• Ensure uploaded audio and image URLs are publicly accessible.
• Maximum billable duration is 120 seconds (2 minutes) per job.
• Processing time varies based on audio length, resolution, and current queue load.
• Please ensure your content complies with usage guidelines.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
  "resolution": "480p"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/hunyuan-avatar" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters