LongCat Avatar 1.6 Multi Talking Avatar API

wavespeed-ai/longcat-avatar-1.6/multi

LongCat Avatar 1.6 Multi turns a single image and multiple audio inputs into multi-character talking or singing avatar videos, making it suitable for digital humans, virtual presenters, dialogue scenes, social content, and multi-speaker avatar workflows. Ready-to-use REST inference API, best performance, 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 1.6 Multi

What is LongCat Avatar 1.6 Multi?

LongCat Avatar 1.6 Multi animates a single image containing two people from two distinct audio tracks, producing realistic, lip-synchronized multi-character video with calmer, more natural expressions and gestures, and identity preserved across long clips.

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 separately. The speaking order determines how these durations are combined, with a minimum billed duration of 3 seconds and a maximum of 64 seconds. The per-5-second prices below are rate equivalents, not 5-second billing increments.

Output ResolutionCost per 5 secondsMax Billed Length
480p$0.2064 seconds
720p$0.4064 seconds

Billing Rules

  • Standard Rate: $0.04/s
  • HD (720p) Rate: $0.08/s (Double the Standard Rate)
  • Minimum Charge: All videos are billed for a minimum of 3 seconds: $0.12 at 480p or $0.24 at 720p.
  • Billing Cap: Billing is capped at 64 seconds.
  • order=meanwhile: take the longer of the two separately rounded-up audio durations, then apply the 3-second minimum and 64-second cap.
  • order=left_right / right_left: add the two separately rounded-up audio durations, then apply the 3-second minimum and 64-second cap. For example, 10.1s + 10.1s is billed as 11s + 11s = 22s.

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

  • Clips support approximately 64 seconds per job. Longer combined audio is truncated to the supported processing window; this is separate from the 64-second billing cap.

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 1.6 Multi API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/longcat-avatar-1.6/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 1.6 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-1.6/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-1.6/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-1.6/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 1.6 Multi API — Frequently asked questions

What is the Longcat Avatar 1.6 Multi API?

Longcat Avatar 1.6 Multi is a WaveSpeedAI model for talking-avatar generation, exposed as a REST API on WaveSpeedAI. LongCat Avatar 1.6 Multi turns a single image and multiple audio inputs into multi-character talking or singing avatar videos, making it suitable for digital humans, virtual presenters, dialogue scenes, social content, and multi-speaker avatar workflows. 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 Longcat Avatar 1.6 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-1.6/multi.

How much does Longcat Avatar 1.6 Multi cost per run or per second?

Longcat Avatar 1.6 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 1.6 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-1.6/multi.

How do I get started with the Longcat Avatar 1.6 Multi API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Longcat Avatar 1.6 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-1.6/multi for AI agents and LLMs