Seedream 5.0 Pro 정식 출시 | 이미지 생성기에서 사용해보기 →

LTX 2.3 Lipsync

wavespeed-ai /

LTX-2.3 Lipsync generates talking head videos from audio with synchronized lip movements and natural facial expressions. Built on DiT-based architecture with improved audio-visual alignment quality. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

digital-human
입력

대기 중

$0.1실행당·~10 / $1

예시전체 보기

관련 모델

README

LTX-2.3 Lipsync

LTX-2.3 Lipsync is an advanced AI model that generates talking head videos from audio and an optional reference image. Built on the LTX-2.3 DiT-based architecture with improved audio-visual quality, it creates realistic lip-synced videos that match your audio input.

Why Choose This?

  • Improved quality Enhanced audio-visual alignment with better lip sync accuracy and natural facial movements.

  • Audio-driven generation Automatically generates video with synchronized lip movements from audio input.

  • Optional reference image Provide a portrait image to use as the base, or let the model use a default portrait.

  • Flexible resolution Supports 480p, 720p, and 1080p outputs to balance quality and cost.

  • Automatic duration Video length automatically matches audio duration (5-20 seconds).

Parameters

ParameterRequiredDescription
audioYesAudio file URL - duration determines video length (5-20s)
imageNoReference portrait image (optional)
promptNoText prompt to guide generation style and motion
resolutionNoOutput resolution: 480p, 720p (default), or 1080p
seedNoRandom seed for reproducibility (-1 for random)

Resolution Options

ResolutionBest For
480pFast previews, iteration, lowest cost
720pBalanced quality and cost (default)
1080pFinal delivery, maximum detail

How to Use

  1. Upload your audio — the audio track that drives the video (5-20 seconds).
  2. Upload reference image (optional) — a portrait to use as the base character.
  3. Add prompt (optional) — describe the style or motion you want.
  4. Select resolution — 480p for iteration, 720p for balance, 1080p for final output.
  5. Run — submit and download the lip-synced video.

Pricing

Pricing is based on audio duration (automatically detected):

Resolution5s10s15s20s
480p$0.10$0.20$0.30$0.40
720p$0.15$0.30$0.45$0.60
1080p$0.20$0.40$0.60$0.80

Best Use Cases

  • Talking Head Videos — Generate spokesperson videos from audio recordings.
  • Content Localization — Create videos in multiple languages from audio tracks.
  • Virtual Presenters — Generate AI presenters for training, marketing, or education.
  • Audio-to-Video — Convert podcasts or audio content into video format.
  • Character Animation — Bring portraits to life with synchronized speech.

Pro Tips

  • Audio quality directly affects lip sync accuracy - use clear audio.
  • Provide a frontal portrait image for best results.
  • Use prompt to guide facial expressions and style.
  • Iterate at 480p to verify results, then render at higher resolution.
  • Audio duration is automatically detected - no need to specify manually.

Notes

  • Audio duration must be between 5-20 seconds.
  • If no reference image is provided, a default portrait will be used.
  • Video length automatically matches audio duration.

Related Models

참고:이 웹사이트는 제3자가 제공하는 AI 모델을 사용합니다.

Ltx 2.3 Lipsync API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2.3/lipsync 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 Ltx 2.3 Lipsync below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "resolution": "720p",
    "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/ltx-2.3/lipsync" \
  -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/ltx-2.3/lipsync";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
        "resolution": "720p",
        "seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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 = {
    "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "resolution": "720p",
    "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/ltx-2.3/lipsync", 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)

Ltx 2.3 Lipsync API — Frequently asked questions

What is the Ltx 2.3 Lipsync API?

Ltx 2.3 Lipsync is a WaveSpeedAI model for talking-avatar generation, exposed as a REST API on WaveSpeedAI. LTX-2.3 Lipsync generates talking head videos from audio with synchronized lip movements and natural facial expressions. Built on DiT-based architecture with improved audio-visual alignment quality. 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 Ltx 2.3 Lipsync 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/ltx-2.3-lipsync.

How much does Ltx 2.3 Lipsync cost per run?

Ltx 2.3 Lipsync starts at $0.10 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 Ltx 2.3 Lipsync 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/ltx-2.3-lipsync.

How long does Ltx 2.3 Lipsync take to generate?

Median end-to-end generation time on WaveSpeedAI is around 118 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 Ltx 2.3 Lipsync 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.

LTX 2.3 Lipsync | AI Digital Human API | WaveSpeedAI