Kwaivgi Kling V1 AI Avatar Pro

Kwaivgi Kling V1 AI Avatar Pro

Playground

Kling AI Avatar Pro converts audio into talking video portraits; pricing is $1 for the first 5s then $0.20/s up to 600s. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

kling-v1-ai-avatar-pro turns a single portrait into a realistic talking-head video driven by your audio. It produces clean lip-sync, natural eye blinks, subtle head motion, and expressive timing suitable for ads, product explainers, education, and virtual hosts.

Highlights

• High-fidelity lip-sync aligned to phonemes and pauses
• Natural micro-expressions, eye blinks, and head motion for lifelike delivery
• Works from one image; preserves identity and lighting
• Optional style guidance via prompt for framing, vibe, and pacing
• Built for production: stable outputs from licensed training data

Parameters

• audio (required): speech or voice track. The model derives duration from the audio.
• image (required): a clear, front-facing portrait (URL or upload).
• prompt (optional): short guidance for style, mood, camera framing, or background.

Recommended inputs

• Photo: frontal face, even lighting, no heavy occlusions; 512 px or larger
• Audio: clean speech, 16–48 kHz, minimal music or reverb

How to Use

1. Upload or paste the audio URL.
2. Upload or paste the portrait image URL.
3. (Optional) Add a short prompt describing style or background tone.
4. Press Run and download the generated avatar video.

> Tips

• Trim long silences at the head and tail of the audio for snappier timing and lower cost.
• For business use, prepare a neutral background and consistent headroom across images.
• Use high-quality microphones or TTS to avoid muffled consonants.

Pricing

• Price per second: $0.20

Billing rules

1. Minimum charge: 5 seconds.
2. Exact-length billing: after the 5-second minimum, price = audio duration (in seconds) × $0.20, up to the cap.
3. Maximum billable length: 600 seconds (10 minutes) → $120.00 cap.
4. Currency rounding: totals are rounded to the nearest cent.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-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"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-v1-ai-avatar-pro" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(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' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  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

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters