Kwaivgi Kling Video To Audio

Kwaivgi Kling Video To Audio

Playground

Try it on WaveSpeedAI!

Kling Video-to-Audio auto-generates or extracts matching sound effects and audio tracks from video using KlingAI’s audio generation model. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.

Features

Kling Video-to-Audio adds a complete soundtrack to a silent video using two short prompts: one for sound effects (SFX) and one for background music (BGM). It generates synchronized foley, ambience, and score cues that match on-screen action. Great for trailers, shorts, product shots, and mood pieces.


Highlights

  • Prompt-based SFX and BGM that follow scene energy and timing
  • Optional ASMR mode for hyper-detailed, close-mic textures
  • Works with cinematic, documentary, gameplay, and product footage
  • Fast iteration: tweak prompts, re-render, and compare

Parameters

  • video (required) URL or upload of the silent clip to be sonified.

  • sound_effect_prompt Describe on-screen events and textures to hear. Example: “Thunderstorm, heavy rain, distant thunder rolls, glass rattling, wind gusts, ocean waves slamming rocks.”

  • bgm_prompt Describe musical mood, instrumentation, and pacing. Example: “Brooding orchestral score, low strings, sparse piano hits, slow build with sub-bass swells.”

  • asmr_mode (checkbox) Enhances micro-details and proximity effect for immersive listening (ear-tingles, crisp foley).


How to Use

  1. Upload or paste the video URL.
  2. Write a concise sound_effect_prompt for foley/ambience.
  3. Add a bgm_prompt for the musical bed.
  4. Toggle asmr_mode if you want ultra-detailed textures.
  5. Click Run and download the generated audio track aligned to your clip.

Prompting Tips

  • Be concrete: call out specific events, materials, and distances

“Leather jacket rustle, footsteps on wet concrete, elevator ding, neon hum.”

  • For BGM, specify tempo/structure.
  • Keep SFX and BGM prompts stylistically consistent to avoid clashes.
  • If dialogue is needed, add it in post—this model focuses on SFX and score.

Output

  • An audio track designed to sync with the input video’s duration.
  • Format and delivery follow platform defaults (download URL in the response).

Pricing

  • Per-job pricing is $0.035

Notes

  • Start with clean, final-cut footage; large edits after sound design will desync cues.
  • Loudness is unmastered by design—normalize or master in your editor to your target LUFS.
  • Ensure you have rights to the video content you upload and follow platform policies for generated audio.

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'
{
  "asmr_mode": false
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-video-to-audio" \
  -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

ParameterTypeRequiredDefaultRangeDescription
videostringNo-The video for generating the output.Please note that the duration cannot exceed 20s.
sound_effect_promptstringNo--Text prompt for sound effect generation, maximum 200 characters
bgm_promptstringNo--Text prompt for background music generation, maximum 200 characters
asmr_modebooleanNofalse-Enable ASMR mode to enhance detailed sound effects, suitable for immersive content scenarios

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to poll for the prediction result
data.statusstringStatus: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.