Kwaivgi Kling Text To Audio

Kwaivgi Kling Text To Audio

Playground

Kling Text-to-Audio turns text prompts into custom sound effects for videos, games, and multimedia using KlingAI’s audio model. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Generate cinematic sound effects directly from text. Describe the scene or action, and Kling creates matching foley, ambience, risers, booms, whooshes, and textures—perfect for trailers, shorts, games, podcasts, and multimedia projects.

Key Features

• Text-to-audio SFX with scene-aware textures and timing
• Wide palette: weather, impacts, machinery, footsteps, creatures, atmospheres
• Clean renders ready for layering and post-mix
• Fast iteration for cue sheets and temp tracks

Parameters

• prompt

Describe what you want to hear. Example: Cold winter night with howling wind across barren fields; deep gusts; distant creaks; approaching snowstorm tension.

• duration

Length of the generated SFX bed in seconds.

How to Use

1. Write a concise, concrete prompt naming sources, space, and mood.
2. Set the duration to match your shot or loop length.
3. Run and download the audio. Trim or loop in your DAW as needed.

Output

• Single SFX track aligned to your requested duration.
• Format follows platform defaults with a downloadable URL.

Pricing

• Just $0.035 per run!!!

Prompting Tips

• Call out materials and distance: metal gate clang close, wood door thud mid, crowd murmur far.
• Add pacing: slow build, big hit at 0:08, decay to silence.
• For loops, keep the ending sparse or symmetrical for seamless repeats.
• Generate stems by running separate prompts for ambience, impacts, and ear-candy, then mix.

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'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "duration": 10
}
JSON
)

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

Response Parameters

Result Request Parameters

Result Response Parameters