Seedream 5.0 Pro 提供開始 | 画像ジェネレーターで試す →

Wan 2.1 Multitalk

wavespeed-ai /

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.

digital-human
入力

待機中

$0.151回あたり·~66 / $10

サンプルすべて表示

関連モデル

README

MultiTalk

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:

ComponentFunction
MultiTalk CoreAudio-to-motion synthesis with perfect lip synchronization
Wan2.1Video diffusion model for realistic human anatomy, expressions, and movements
Uni3CCamera controlnet for dynamic, professional-looking scene control

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

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

MetricCost
Per 5 seconds$0.15

Billing Rules

  • Minimum charge: 5 seconds ($0.15)
  • 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

Audio LengthBilled DurationCalculationTotal Cost
3s5s (minimum)5 ÷ 5 × $0.15$0.15
12s15s15 ÷ 5 × $0.15$0.45
30s30s30 ÷ 5 × $0.15$0.90
1m (60s)60s60 ÷ 5 × $0.15$1.80
5m (300s)300s300 ÷ 5 × $0.15$9.00
10m (600s)600s (maximum)600 ÷ 5 × $0.15$18.00

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

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.
注記:本サイトは第三者が提供するAIモデルを使用しています。

Wan 2.1 Multitalk API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.1/multitalk with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Wan 2.1 Multitalk below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_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 "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; 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' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$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
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.1/multitalk";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
        "seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "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
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.1/multitalk", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Wan 2.1 Multitalk API — Frequently asked questions

What is the Wan 2.1 Multitalk API?

Wan 2.1 Multitalk is a WaveSpeedAI model for talking-avatar generation, exposed as a REST API on WaveSpeedAI. 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. You can call it programmatically or try it from the playground above.

How do I call the Wan 2.1 Multitalk API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/wan-2.1-multitalk.

How much does Wan 2.1 Multitalk cost per run?

Wan 2.1 Multitalk starts at $0.15 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Wan 2.1 Multitalk accept?

Key inputs: `prompt`, `image`, `audio`, `seed`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/wan-2.1-multitalk.

How long does Wan 2.1 Multitalk take to generate?

Median end-to-end generation time on WaveSpeedAI is around 208 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Wan 2.1 Multitalk outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

Wan 2.1 Multitalk | AI Digital Human API | WaveSpeedAI