Seedream 5.0 Pro уже здесь | Попробуйте в Генераторе изображений →
Войти

LTX 2 19B Lipsync

wavespeed-ai /

LTX-2 Lipsync generates synchronized talking head videos from a reference image and audio input. Powered by the 19B DiT architecture, it produces high-fidelity lip-synced videos with natural head movements. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

digital-human
Ввод

Ожидание

$0.1за запуск·~10 / $1

ПримерыСмотреть всё

bear looks into the camera and begin to talk

A weathered elderly man with a gentle, slightly weary expression sits in a sunlit garden chair, his hands resting loosely in his lap. He wears a faded, button-up shirt and worn trousers, with a subtle smile playing on his lips as he speaks softly, his voice warm and thoughtful. His eyes, lined with age but still bright, look slightly off-camera as if engaged in a candid, unscripted conversation with someone nearby. The background is softly blurred, showing greenery and dappled sunlight, enhancing the natural, relaxed atmosphere. The scene feels intimate and authentic — no forced performance, just the quiet truth of a man sharing his thoughts in a moment of peace.

Похожие модели

README

LTX-2 19B Lipsync

LTX-2 Lipsync is an audio-driven digital human model that generates synchronized talking head videos from a reference image and audio input. Powered by the 19B-parameter DiT (Diffusion Transformer) architecture, it produces high-fidelity lip-synced videos with natural head movements and expressions.

Why Choose This?

  • Audio-driven generation Simply provide an audio file and optional reference image — the model handles lip-sync, head motion, and expressions automatically.

  • High-fidelity output Leverages the 19B-parameter LTX-2 architecture for detailed, temporally consistent video with natural mouth movements.

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

  • Variable duration Video length is automatically determined by audio duration (5-20 seconds max).

Parameters

ParameterRequiredDescription
audioYesAudio file URL for lip-sync (determines video length)
imageNoReference portrait image (JPG or PNG)
promptNoOptional text to guide generation style
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 file that drives lip-sync and determines video duration.
  2. Upload your image (optional) — the reference portrait that defines the speaker's appearance.
  3. Write your prompt (optional) — describe any style or motion preferences.
  4. Select resolution — 480p for iteration, 720p for balance, 1080p for final output.
  5. Run — submit and download the lip-synced video.

Pricing

Resolution5s10s15s20s
480p$0.075$0.15$0.225$0.30
720p$0.10$0.20$0.30$0.40
1080p$0.15$0.30$0.45$0.60

Billing Rules

  • Base price: $0.10 (720p, 5 seconds)
  • Duration: Determined by audio length (min 5s, max 20s billing)
  • Resolution multiplier: 480p = 0.75×, 720p = 1×, 1080p = 1.5×
  • Total cost = duration × $0.10 × resolution_multiplier / 5

Best Use Cases

  • Digital Avatars — Create talking head videos for virtual presenters and avatars.
  • Content Creation — Generate lip-synced videos for social media and marketing.
  • Localization — Dub existing content with new audio while maintaining visual consistency.
  • Accessibility — Create sign language or narrated content with synchronized visuals.
  • Education — Produce instructional videos with talking head presenters.

Pro Tips

  • Use clear, high-quality audio for best lip-sync results.
  • Provide a front-facing portrait image with visible mouth for optimal generation.
  • Use high-quality, sharp, well-lit portrait images for best results.
  • Iterate at 480p to dial in results, then render at higher resolution for final output.
  • Use fixed seed when comparing variations to isolate changes.

Notes

  • Maximum video duration is 20 seconds (determined by audio length).
  • Audio longer than 20 seconds will be truncated.
  • The aspect ratio of output video is influenced by your input image.

Related Models

Примечание:Этот сайт использует модели ИИ, предоставляемые третьими лицами.

Ltx 2 19b Lipsync API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2-19b/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 19b 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-2-19b/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-2-19b/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-2-19b/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 19b Lipsync API — Frequently asked questions

What is the Ltx 2 19b Lipsync API?

Ltx 2 19b Lipsync is a WaveSpeedAI model for talking-avatar generation, exposed as a REST API on WaveSpeedAI. LTX-2 Lipsync generates synchronized talking head videos from a reference image and audio input. Powered by the 19B DiT architecture, it produces high-fidelity lip-synced videos with natural head movements. 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 19b 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-2-19b-lipsync.

How much does Ltx 2 19b Lipsync cost per run?

Ltx 2 19b 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 19b 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-2-19b-lipsync.

How long does Ltx 2 19b Lipsync take to generate?

Median end-to-end generation time on WaveSpeedAI is around 87 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 19b 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 19B Lipsync | AI Digital Human API | WaveSpeedAI