kwaivgi/kling-video-to-audio
kwaivgi/kling-video-to-audio
kwaivgi/kling-video-to-audio. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
相關模型
完整參數參考、輸出結構與即時價格
| AI 模型 API 市集 | 一個平台,全部完成 | 最受歡迎 | 服務條款 | 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。 |
|---|---|---|---|---|
| video *Video | video_upload | — | video/* | |
| sound_effect_promptSound Effect Prompt | textarea | — | ≤ 200 chars | |
| bgm_promptBgm Prompt | textarea | — | ≤ 200 chars | |
| asmr_modeAsmr Mode | boolean | false | — |
完整參數參考、輸出結構與即時價格
| 深入了解 | 一個平台,全部完成 | 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。 |
|---|---|---|
| videos | array<string> |
API
瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/kwaivgi/kling-video-to-audio" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"video": "https://assets-public.namifusion.com/marketplace/videos/2026-04-14/88d6efad3763.mp4",
"asmr_mode": false
}
}'
# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
-H "Authorization: Bearer YOUR_API_KEY"Python
import time, requests
API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}
# 1) Submit
resp = requests.post(
"https://www.namifusion.com/api/v1/marketplace/run/kwaivgi/kling-video-to-audio",
headers=HEADERS,
json={
"input": {
"video": "https://assets-public.namifusion.com/marketplace/videos/2026-04-14/88d6efad3763.mp4",
"asmr_mode": False
}
},
)
resp.raise_for_status() # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()
# 2) Poll until a terminal state (completed / failed / cancelled).
# This model is allowed up to 300s server-side.
deadline = time.time() + 360
while task.get("status") not in ("completed", "failed", "cancelled"):
if time.time() > deadline:
raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
time.sleep(3)
poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
poll.raise_for_status()
task = poll.json()
print(task["status"], task.get("output"))JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };
// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/kwaivgi/kling-video-to-audio", {
method: "POST",
headers: { ...HEADERS, "Content-Type": "application/json" },
body: JSON.stringify({
"input": {
"video": "https://assets-public.namifusion.com/marketplace/videos/2026-04-14/88d6efad3763.mp4",
"asmr_mode": false
}
}),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();
// 2) Poll until a terminal state (completed / failed / cancelled).
// This model is allowed up to 300s server-side.
const deadline = Date.now() + 360 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
await new Promise((r) => setTimeout(r, 3000));
const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
task = await poll.json();
}
console.log(task.status, task.output);API 文件
kwaivgi/kling-video-to-audio
Generate synchronized sound effects and background music from video with no cold start and production-friendly cost.
kwaivgi/kling-video-to-audio is an AI model for video-to-audio generation that automatically creates or extracts matching sound effects and audio tracks from an input video. Using short prompts for SFX and BGM, it enables fast, controllable soundtrack creation for silent clips while maintaining strong alignment with scene timing, motion, and mood.
Built on KlingAI’s audio generation capabilities, this model is well suited for teams that need fast turnaround, affordable per-job pricing, and reliable runtime performance. It is especially effective for trailers, short-form content, product videos, and atmospheric visual pieces.
🚀 Key Features
- Video-conditioned audio generation: Produces sound effects and background music that follow the visual action, pacing, and energy of the source video.
- Dual-prompt control: Separate prompts for SFX and BGM make it easier to shape foley, ambience, musical tone, and overall emotional direction.
- Optional ASMR mode: Enhances micro-detail and close-mic texture for more immersive, tactile listening experiences.
- Fast creative iteration: Quickly refine prompts, re-render outputs, and compare variations during sound design exploration.
- Broad footage compatibility: Works well with cinematic, documentary, gameplay, and product-focused video content.
- No cold start, cost-efficient: Designed for responsive production workflows where consistency and unit economics matter.
🛠️ Technical Specifications
| Item | Details |
|---|---|
| Model | kwaivgi/kling-video-to-audio |
| Model architecture | Video-to-audio generation model |
| Core capability | Generates synchronized SFX and BGM for input video |
| Input Format | Video, sound effect prompt, background music prompt, ASMR mode toggle |
| Output Format | Audio |
| Duration | Input video up to 20 seconds |
| Sound effect prompt length | Up to 200 characters |
| BGM prompt length | Up to 200 characters |
| ASMR mode | Supported(default: false) |
| Synchronization | Output audio is designed to match the input video duration |
| Recommended source material | Silent clips or videos requiring sound design enhancement |
| Latency | Fast platform-level inference; actual runtime depends on content and system load |
| Cold start | None |
Sample Prompts
Sound effect prompt examples
Thunderstorm, heavy rain, distant thunder rolls, glass rattling, wind gusts, ocean waves slamming rocks.Leather jacket rustle, footsteps on wet concrete, elevator ding, neon hum.
BGM prompt examples
Brooding orchestral score, low strings, sparse piano hits, slow build with sub-bass swells.Minimal electronic ambience, slow tempo, soft synth pads, gradual tension build.
💰 Pricing
| Pricing Item | Price |
|---|---|
| Base price per job | $0.035 |
💡 Best Use Cases
- Short-form and social media video: Add polished sound design to silent clips for stronger engagement and emotional impact.
- E-commerce and product marketing: Enhance product visuals with tactile SFX, ambience, and branded musical mood.
- Trailers and mood films: Rapidly generate soundtrack concepts for pitch decks, previews, and creative prototypes.
- Game and film pre-production: Create temporary or exploratory audio beds for animatics, rough cuts, and internal reviews.
🔗 Related Models
This listing covers kwaivgi/kling-video-to-audio, focused on generating audio from video input. If you are evaluating the broader Kling family, you may also consider related variants for video generation, editing, or higher-end production workflows depending on your pipeline requirements.