Skywork AI Skyreels V3 Pro Single Avatar API Documentation

Skywork AI Skyreels V3 Pro Single Avatar API Documentation

Playground

SkyReels V3 Pro Single Avatar is a high-quality AI talking avatar video generation model that creates audio-driven avatar videos from one image, one audio file, and a motion prompt. Ready-to-use REST inference API for digital humans, virtual presenters, product explainers, marketing videos, education content, social media clips, and professional avatar video workflows with simple integration, no coldstarts, and affordable pricing.

Features

Skywork AI SkyReels V3 Pro Single Avatar generates a talking avatar video from a single reference image and an audio clip. It is designed for higher-quality avatar performance, with stronger realism, smoother facial animation, and more polished lip-sync than the Standard variant, making it suitable for digital presenters, spokesperson videos, short-form content, and character-driven speaking clips.

Why Choose This?

• Higher-quality avatar generation The Pro variant is built for stronger visual quality, more natural expression, and more refined speaking performance.

• Single-image avatar workflow Turn one portrait image into a speaking avatar video.

• Audio-driven lip-sync Use an uploaded audio clip to drive speech timing and mouth movement.

• Prompt-guided behavior Add a short prompt to influence expression, delivery style, or overall presentation.

• Simple production workflow Upload an image, upload audio, write a prompt, and generate a polished talking avatar clip.

• Production-ready API Suitable for virtual presenters, social content, marketing spokespeople, and short-form avatar media.

Parameters

How to Use

1. Upload your image — provide a clear portrait image of the person you want to animate.
2. Upload your audio — use a clean audio clip to drive the speaking performance.
3. Write your prompt — describe the desired motion, expression, or delivery style.
4. Submit — run the model and download the generated avatar video.

Example Prompt

Let the man speak naturally with subtle head movement, calm expression, and realistic lip-sync.

Pricing

Pricing is based on the uploaded audio duration.

Billing Rules

• Pricing is $0.08 per second
• Total price = $0.08 × audio duration
• Longer audio increases cost linearly

Best Use Cases

• Talking portrait videos — Animate a single portrait into a speaking clip.
• Digital spokesperson content — Create presenter-style videos for announcements, marketing, or onboarding.
• Virtual presenters — Generate clean speaking-avatar videos for explainers and business content.
• Short-form social media clips — Turn portraits and voice clips into speaking content quickly.
• Narration-based character videos — Pair a portrait with speech audio for expressive delivery.

Pro Tips

• Use a clear, front-facing portrait for better avatar stability and facial animation.
• Upload clean audio for stronger lip-sync and more natural speaking performance.
• Keep the prompt simple and focused on expression or delivery style.
• Shorter audio clips are easier to test when iterating on quality.
• Use the Pro variant when you want better realism and polish than the Standard workflow.

Notes

• prompt, image, and audio are required.
• Pricing depends on the uploaded audio duration.
• A clean portrait and high-quality audio generally improve results.
• This workflow is intended for single-avatar speaking video generation.

Related Models

• Skywork AI SkyReels V3 Standard Single Avatar — Standard single-avatar workflow at a lower price point.
• Skywork AI SkyReels V3 Standard Multi Avatar — Multi-avatar workflow in the Standard product line.
• Skywork AI SkyReels V3 Pro Multi Avatar — Higher-tier multi-avatar generation for more advanced character scenes.

Duration limit

The maximum supported audio duration is 200 seconds. Longer audio is automatically trimmed to 200 seconds before processing.

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'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "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"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/skywork-ai/skyreels-v3-pro/single-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