kwaivgi/kling-video/video-to-audio
Kling Video Video To Audio by KwaiVGI - advanced AI model for video-to-audio. Delivers high-quality results with fast inference, suitable for both creative and production workflows.
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runkwaivgi/kling-video/video-to-audioInput Schema
4 parameters · 0 required · 4 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
video | string | Optional | The video URL to extract audio from. Only .mp4/.mov formats are supported. File size does not exceed 100MB. Video duration between 3.0s and 20.0s. |
asmr_mode | boolean | Optional | Enable ASMR mode. This mode enhances detailed sound effects and is suitable for highly immersive content scenarios. · Default: false |
sound_effect_prompt | string | Optional | Sound effect prompt. Cannot exceed 200 characters. · Max length: 200 · Default: "Car tires screech as they accelerate in a drag race" |
background_music_prompt | string | Optional | Background music prompt. Cannot exceed 200 characters. · Max length: 200 · Default: "intense car race" |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "kwaivgi/kling-video/video-to-audio",
"video": "https://static.sandbase.ai/examples/kwaivgi/kling-video/video-to-audio/output_url_0.mp4",
"asmr_mode": false,
"sound_effect_prompt": "Car tires screech as they accelerate in a drag race",
"background_music_prompt": "intense car race",
"prompt": "a beautiful sunset over mountains"
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Kling Video
Kling Video is a video-conditioned soundtrack creation endpoint in the Kling family. It is built for creators who need to turn a concrete creative brief into a controlled visual sequence: the request establishes the source material, the intended subject behavior, the camera language, and the atmosphere of the finished shot. The standard route keeps that workflow explicit instead of hiding its input assumptions behind a generic video-generation label.
In practice, this route accepts video as creative context and exposes focused generation controls for delivery planning. That makes it suitable for shot-based pipelines where teams must preserve a source, direct a transformation, or control the final format without losing sight of the model's central task. Write prompts as a compact shot plan—subject, action, setting, camera, light, and timing—then use the structured fields for constraints that should remain deterministic across iterations.
Highlights
- Sound designed from picture. Conditions sound effects and music on the timing and visual events of an uploaded video.
- Separate sound directions. Independent prompts for effects and background music make the soundtrack easier to art-direct.
- ASMR detail mode. A dedicated ASMR switch emphasizes close, detailed sound effects for immersive footage.
- Short-form clip support. Accepts MP4 or MOV source clips from 3 to 20 seconds and up to 100 MB.
Pricing
| Billing unit | Price |
|---|---|
| Base request | $0.035000 |
When to Use
| Scenario | Recommendation |
|---|---|
| Choose this route | Use it when the deliverable specifically calls for video-conditioned soundtrack creation, rather than a neighboring generation mode. |
| Prepare the source | Provide video in the format described by the request schema. |
| Direct the shot | Describe the subject, action, environment, camera movement, lighting, and temporal progression in that order. |
| Control continuity | Use endpoint frames, reference media, strength, or audio controls when those fields are available instead of burying hard constraints in prose. |
| Plan delivery | Set duration, frame count, resolution, and aspect ratio explicitly when the schema exposes them, then compare iterations with a stable seed where supported. |
Prompt Guide
For video-conditioned soundtrack creation, describe one coherent shot rather than a list of visual keywords. Put the main subject and action first, follow with location and staging, then add camera movement, lens or framing, lighting, mood, and any timed change. Keep URLs and hard delivery choices in their dedicated fields.
{
"video": "https://static.sandbase.ai/examples/kwaivgi/kling-video/video-to-audio/output_url_0.mp4"
}
Technical Specs
| Specification | Value |
|---|---|
| Model ID | kwaivgi/kling-video/video-to-audio |
| Required inputs | None declared |
| Execution | Asynchronous generation job |
| Request controls | 4 documented fields |
| Output | url, content_type |
Request fields
| Field | Type and constraints |
|---|---|
video | string; Optional |
asmr_mode | boolean; Optional; Default: false |
sound_effect_prompt | string; Optional; Default: "Car tires screech as they accelerate in a drag race" |
background_music_prompt | string; Optional; Default: "intense car race" |