LongCat Avatar 1.5 Multi Digital Human API

wavespeed-ai/longcat-avatar-1.5/multi

LongCat Avatar 1.5 Multi converts a single image and two audio inputs into multi-character talking or singing videos at up to 720p, capped at 64 seconds per clip. Ready-to-use REST API, no coldstarts, affordable pricing.

Talking Avatar
Input

Drag & drop or click to upload

preview

Drag & drop or click to upload

Drag & drop or click to upload

Idle

$0.04per run·~25 / $1

ExamplesView all

Related Models

README

LongCat Avatar 1.5 Multi

What is LongCat Avatar 1.5 Multi?

LongCat Avatar 1.5 Multi animates a single image containing two people from two distinct audio tracks, producing super-realistic, lip-synchronized multi-character video with natural dynamics and identity preserved across frames.

Why it looks great

  • Per-speaker lip sync: each speaker's mouth tracks its own audio precisely.

  • Full-body coherence: head motion, facial expressions, and posture align with the assigned audio for each speaker.

  • Identity preservation: both faces remain visually consistent throughout the clip.

  • Flexible turn-taking: choose between simultaneous speech and ordered turn-taking via the order parameter.

Pricing

Billing duration: Each input audio duration is rounded up to whole seconds. The minimum billed duration is 3 seconds; shorter inputs are billed as 3 seconds. Billing is per second of video, and 720p costs twice as much as 480p.

Price of one run, where both the left audio and the right audio have the same length (the length of each audio is in the column header):

Order and resolutionEach audio 1 sEach audio 5 sEach audio 10 sEach audio 30 sEach audio 60 s
order=meanwhile, 480p$0.12$0.20$0.40$1.20$2.40
order=meanwhile, 720p$0.24$0.40$0.80$2.40$4.80
order=left_right, 480p$0.12$0.40$0.80$2.40$2.56
order=left_right, 720p$0.24$0.80$1.60$4.80$5.12

order=right_left is priced the same as order=left_right.

Billing Rules

  • order=meanwhile: billed by the longer of the left audio and the right audio.
  • order=left_right / right_left: billed by the left audio duration plus the right audio duration (both audios played sequentially).
  • Default settings: a run with all defaults costs $0.12 per run.
  • Minimum Charge: All videos are billed for a minimum of 3 seconds. With order=meanwhile and each audio 1 s, that is $0.12 at 480p and $0.24 at 720p.
  • Billing Cap: Billing is capped at 64 seconds. With order=meanwhile and each audio 90 s, the price is $2.56 at 480p and $5.12 at 720p.

How to Use

  1. Upload the left_audio and right_audio files.
  2. Upload your image (it should clearly show two people, left and right).
  3. Select the speaking order (left_right, right_left, or meanwhile).
  4. Select the resolution (480p or 720p).
  5. (Optional) Add a prompt to guide expression, style, or pose.
  6. Submit the job and download the result once it's ready.

Note

  • Max clip length per job: up to 64 seconds. Longer audio is automatically trimmed.
  • Processing speed: approximately 10-30 seconds of wall time per 1 second of video (varies by resolution and queue load).

More Versions

Related Models

  • InfiniteTalk — Higher-end avatar video workflow for more advanced speaking performance.
  • InfiniteTalk Multi — Multi-character avatar workflow for more complex scenes.
Note:This website uses AI models provided by third parties. Documentation prices are for reference and may be outdated. The Generate button shows an estimate; the final task charge prevails.

Longcat Avatar 1.5 Multi API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/longcat-avatar-1.5/multi 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 Longcat Avatar 1.5 Multi 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",
    "left_audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "right_audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "order": "meanwhile",
    "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/longcat-avatar-1.5/multi" \
  -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="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"

# 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' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/longcat-avatar-1.5/multi";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "left_audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
        "right_audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
        "order": "meanwhile",
        "resolution": "480p"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${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", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
  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",
    "left_audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "right_audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "order": "meanwhile",
    "resolution": "480p"
}

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/longcat-avatar-1.5/multi", 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 = 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", "deleted"}:
        raise RuntimeError(result)
    time.sleep(2)

Longcat Avatar 1.5 Multi API — Frequently asked questions

What is the Longcat Avatar 1.5 Multi API?

Longcat Avatar 1.5 Multi is a WaveSpeedAI model for talking-avatar generation, exposed as a REST API on WaveSpeedAI. LongCat Avatar 1.5 Multi converts a single image and two audio inputs into multi-character talking or singing videos at up to 720p, capped at 64 seconds per clip. Ready-to-use REST API, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Longcat Avatar 1.5 Multi 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 Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/longcat-avatar-1.5/multi.

How much does Longcat Avatar 1.5 Multi cost per run or per second?

Longcat Avatar 1.5 Multi starts at $0.04 per run or per second. 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 Longcat Avatar 1.5 Multi accept?

Key inputs: `prompt`, `image`, `resolution`, `seed`, `left_audio`, `order`. 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/longcat-avatar-1.5/multi.

How long does Longcat Avatar 1.5 Multi take to generate?

Reported generation time on WaveSpeedAI is around 679 seconds per request. This is an estimate, not a latency guarantee; queue time and input settings can change the total wait. live status is visible in the prediction record.

Can I use Longcat Avatar 1.5 Multi outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.

llms.txt — wavespeed-ai/longcat-avatar-1.5/multi for AI agents and LLMs