Wan 2.1 Multitalk API Documentation

Wan 2.1 Multitalk API Documentation

Playground

MultiTalk (WAN 2.1) is an audio-driven AI that turns a single image and audio into talking or singing conversational videos. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Transform static photos into dynamic speaking videos with MultiTalk — a revolutionary audio-driven video generation framework by MeiGen-AI. Unlike traditional talking head methods, MultiTalk animates full conversations with realistic lip synchronization, natural body movements, and even multi-person interactions.

Why It Looks Great

• Perfect lip sync: Advanced audio encoding (Wav2Vec) captures speech nuances including rhythm, tone, and pronunciation for precise synchronization.
• Multi-person support: Generate videos with multiple speakers interacting naturally in the same scene.
• Full body animation: Goes beyond facial movements to include natural gestures, expressions, and body language.
• Dynamic camera control: Powered by Uni3C controlnet for subtle camera movements and professional cinematography.
• Prompt-guided generation: Follow text instructions to control scene, pose, and behavior while maintaining audio sync.
• Extended duration: Support for videos up to 10 minutes long.

How It Works

MultiTalk combines three powerful technologies for optimal results:

How to Use

1. Upload your image — provide a photo with one or more people.
2. Upload your audio — add the speech or song you want the subject to perform.
3. Write your prompt (optional) — describe the scene, pose, or behavior you want.
4. Set duration — choose your desired video length.
5. Run — click the button to generate.
6. Download — preview and save your talking video.

Pricing

> Billing duration: Input media duration is rounded up to whole seconds. The minimum billed duration is 3 seconds; shorter inputs are billed as 3 seconds. Existing per-5-second rate tables remain unchanged.

Per 5-second billing based on audio duration. Maximum video length: 10 minutes.

Billing Rules

• Minimum charge: 3 seconds ($0.09)
• Maximum duration: 600 seconds (10 minutes)
• Billed duration: Audio length rounded up to nearest 5-second increment
• Total cost: (Billed duration ÷ 5) × $0.15

Examples

Best Use Cases

• Virtual Presentations — Create professional talking head videos from a single photo.
• Content Localization — Dub videos into different languages with perfect lip sync.
• Music & Performance — Generate singing videos with synchronized mouth movements.
• Conversational Content — Produce multi-person dialogue scenes for storytelling.
• Marketing & Advertising — Create spokesperson videos without filming sessions.

Related Models

• Wan2.1 Text-to-Video / Image-to-Video — For general video generation without audio sync.
• Uni3C Camera Control — For creating custom camera motion transfers.

Pro Tips for Best Results

• Use clear, front-facing photos with visible faces for the best lip synchronization.
• High-quality audio with minimal background noise produces more accurate results.
• For multi-person scenes, ensure all faces are clearly visible in the source image.
• Add scene descriptions in your prompt to enhance the visual context and atmosphere.
• Start with shorter clips to test synchronization before generating longer videos.

Notes

• If using URLs, ensure they are publicly accessible.
• Processing time scales with video duration and complexity.
• Best results come from clear speech audio and well-lit portrait images.
• For singing content, ensure the audio has clear vocal tracks.

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",
  "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.1/multitalk" \
  -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