Seedance 2.5 ya disponible | Pruébalo en el generador de vídeo →

kwaivgi/

Kling TextToVideo by Kwaivgi creates videos with lifelike lip movements that precisely sync to input text for natural speaking visuals. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

digital-human
Entrada

Inactivo

$0.14por ejecución·~71 / $10

EjemplosVer todo

Modelos relacionados

README

Kling Lipsync Text-to-Video

Make any face speak your words with AI-powered lip synchronization. Upload a video, enter your text, choose a voice, and Kling Lipsync will generate realistic lip movements perfectly matched to the synthesized speech — ideal for dubbing, content localization, and creative projects.

Why It Looks Great

  • Realistic lip sync: AI-generated mouth movements accurately match the spoken audio for natural-looking results.
  • Multiple voice options: Choose from a variety of voice characters to match your content style.
  • Bilingual support: Generate speech in English (en) or Chinese (zh).
  • Adjustable speed: Control the speaking pace with the voice speed parameter.
  • Text-driven workflow: Simply type what you want the character to say — no audio recording needed.

Parameters

ParameterRequiredDescription
videoYesSource video with a visible face (upload or public URL).
textYesThe text you want the character to speak.
voice_idYesVoice character selection (e.g., genshin_klee2).
voice_languageNoLanguage for speech synthesis: en (English) or zh (Chinese). Default: en.
voice_speedNoSpeaking speed multiplier. Default: 1.

How to Use

  1. Upload your video — drag and drop or paste a public URL. Ensure the face is clearly visible.
  2. Enter your text — type the words you want the character to speak.
  3. Select voice_id — choose a voice character that fits your content.
  4. Choose language — select en for English or zh for Chinese.
  5. Adjust speed (optional) — modify voice_speed to speak faster or slower.
  6. Run — click the button to generate.
  7. Download — preview and save your lip-synced video.

Pricing

Flat rate per generation.

OutputCost
Per video$0.14

Best Use Cases

  • Content Localization — Dub videos into different languages while maintaining natural lip movements.
  • Social Media & Entertainment — Create fun talking videos, memes, and viral content.
  • E-learning & Training — Generate instructional videos with consistent narration.
  • Marketing & Advertising — Produce multilingual ad variants from a single video shoot.
  • Character Animation — Bring static or animated characters to life with synchronized speech.

Pro Tips for Best Results

  • Use videos with clear, front-facing shots of the face for the most accurate lip sync.
  • Keep text length appropriate for the video duration — shorter clips work best with concise messages.
  • Match the voice character to the visual appearance for more believable results.
  • Test different voice_speed values to find the natural pacing for your content.
  • For multilingual projects, generate separate versions with appropriate voice_language settings.
  • Ensure good lighting on the face in the source video for cleaner lip tracking.

Notes

  • If using a URL for the video, ensure it is publicly accessible. A preview thumbnail confirms successful loading.
  • The face must be clearly visible throughout the video for accurate lip synchronization.
  • Processing time may vary based on video length and current queue load.
  • Best results are achieved with videos where the subject is speaking or has a neutral expression.
Nota:Este sitio web utiliza modelos de IA proporcionados por terceros. Los precios de la documentación son orientativos y pueden estar desactualizados. El botón Generate muestra una estimación; prevalece el cargo final de la tarea.

Kling Lipsync Text To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/kwaivgi/kling-lipsync/text-to-video 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 Kling Lipsync Text To Video below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "text": "A clear example input",
    "voice_id": "genshin_klee2",
    "voice_language": "en",
    "voice_speed": 1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-lipsync/text-to-video" \
  -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/kwaivgi/kling-lipsync/text-to-video";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
        "text": "A clear example input",
        "voice_id": "genshin_klee2",
        "voice_language": "en",
        "voice_speed": 1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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 = {
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "text": "A clear example input",
    "voice_id": "genshin_klee2",
    "voice_language": "en",
    "voice_speed": 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/kwaivgi/kling-lipsync/text-to-video", 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)

Kling Lipsync Text To Video API — Frequently asked questions

What is the Kling Lipsync Text To Video API?

Kling Lipsync Text To Video is a Kuaishou model for talking-avatar generation, exposed as a REST API on WaveSpeedAI. Kling TextToVideo by Kwaivgi creates videos with lifelike lip movements that precisely sync to input text for natural speaking visuals. 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 Kling Lipsync Text To Video 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/kwaivgi/kwaivgi-kling-lipsync-text-to-video.

How much does Kling Lipsync Text To Video cost per run?

Kling Lipsync Text To Video starts at $0.14 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 Kling Lipsync Text To Video accept?

Key inputs: `video`, `text`, `voice_id`, `voice_language`, `voice_speed`. 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/kwaivgi/kwaivgi-kling-lipsync-text-to-video.

How long does Kling Lipsync Text To Video take to generate?

Median end-to-end generation time on WaveSpeedAI is around 149 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 Kling Lipsync Text To Video outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Kuaishou). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

Kling Lipsync Text to Video | AI Digital Human API on WaveSpeedAI