LongCat Avatar 1.6 Digital Human API

wavespeed-ai/longcat-avatar-1.6

LongCat Avatar 1.6 turns a portrait image and audio into talking or singing avatar videos, with natural facial expressions and consistent character appearance for digital humans, virtual presenters, social content, and avatar video 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

Idle

$0.04per run·~25 / $1

ExamplesView all

Related Models

README

LongCat Avatar 1.6

LongCat Avatar 1.6 generates audio-driven avatar videos from a single portrait image. Provide an image and an audio track to create a speaking or singing avatar video, with optional prompt guidance for expression, pose, and motion.

Why Choose This?

  • Audio-driven avatar video — Animate a portrait using speech or singing audio.
  • Speaking and singing workflows — Use different types of vocal audio to drive the avatar performance.
  • Prompt-guided motion — Add optional instructions for expression, pose, or movement.
  • 480p and 720p output — Choose the resolution that fits your workflow.
  • Seed control — Use a fixed seed when comparing generation settings.

Parameters

ParameterRequiredDescription
audioYesAudio file used to drive the speaking or singing performance. Longer audio is truncated to the supported processing window.
imageYesSource portrait image of the person to animate.
promptNoOptional guidance for expression, pose, style, or motion behavior.
resolutionNoOutput resolution: 480p or 720p.
seedNoRandom seed. Use a fixed value when reproducibility is useful.

How to Use

  1. Upload the audio — Provide the speech or singing track that will drive the avatar.
  2. Upload the image — Provide the portrait image to animate.
  3. Add a prompt optional — Describe expression, pose, or motion when additional guidance is needed.
  4. Choose resolution — Select 480p or 720p.
  5. Set a seed optional — Use a fixed seed when comparing variations.
  6. Submit — Generate and retrieve the avatar video.

Pricing

Pricing is based on the input audio duration and selected resolution. Billing is per second of audio, and 720p costs twice as much as 480p for the same audio.

ResolutionDefault run5 s audio
480p$0.12$0.20
720p$0.24$0.40

Audio duration is rounded up to whole seconds for billing, with a minimum billed duration of 3 seconds and a maximum of 64 seconds. Audio shorter than 3 seconds is billed as 3 seconds, and audio longer than 64 seconds is billed as 64 seconds.

Audio Duration480p720p
3 s (minimum)$0.12$0.24
10 s$0.40$0.80
30 s$1.20$2.40
64 s (maximum)$2.56$5.12

Prompt and seed do not add separate charges.

Best Use Cases

  • Talking portraits — Animate a still portrait using recorded speech.
  • Virtual presenters — Create avatar-led presentations and explainers.
  • Singing avatars — Animate a portrait using singing audio.
  • Creator content — Generate avatar videos for social and promotional workflows.
  • Personalized videos — Pair portrait images with custom audio recordings.

Pro Tips

  • Use a clear portrait with the face visible.
  • Clear audio with limited background noise is recommended.
  • Keep prompt guidance focused on expression, pose, or motion.
  • Use a fixed seed when comparing prompt variations with the same inputs.

Notes

  • Default generation supports up to approximately 64 seconds of output.
  • Audio longer than the supported processing window is truncated rather than processed in full.

Related Models

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 API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/longcat-avatar-1.6 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 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",
    "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" \
  -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";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
        "resolution": "480p"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${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",
    "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "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", 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 API — Frequently asked questions

What is the Longcat Avatar 1.6 API?

Longcat Avatar 1.6 is a WaveSpeedAI model for talking-avatar generation, exposed as a REST API on WaveSpeedAI. LongCat Avatar 1.6 turns a portrait image and audio into talking or singing avatar videos, with natural facial expressions and consistent character appearance for digital humans, virtual presenters, social content, and avatar video 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 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.

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

Longcat Avatar 1.6 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 accept?

Key inputs: `prompt`, `image`, `audio`, `resolution`, `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/longcat-avatar-1.6.

How long does Longcat Avatar 1.6 take to generate?

Reported generation time on WaveSpeedAI is around 515 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 1.6 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 for AI agents and LLMs