Use Videos Lip Sync with Comfy Router

Call kling/videos-lip-sync through Comfy Router: endpoint, request shape and the response Router returns.

API Reference for kling/videos-lip-sync, served by Comfy Router from Kling.

Quick start

Create a key at platform.comfy.org/profile/api-keys and export it as COMFY_API_KEY. The Python and TypeScript snippets use the Comfy SDKs (pip install comfy-sdk, npm install @comfyorg/sdk); the cURL snippet is the same call over raw HTTP.

Model ID: kling/videos-lip-sync

Endpoint: POST https://api.comfy.org/v2/models/kling/videos-lip-sync

Python

from comfy_sdk import Comfy

# Reads COMFY_API_KEY from the environment. Each call sends a fresh
# Idempotency-Key and waits up to 10 minutes for the finished result.
with Comfy() as client:
    result = client.models.run(
        "kling/videos-lip-sync",
        {
            "input": {
                "mode": "text2video",
                "text": "Welcome to Comfy Cloud.",
                "video_id": "kling-video-6f5e4d3c2b1a",
                "voice_id": "genshin_vindi2",
                "voice_language": "en",
                "voice_speed": 1,
            },
        },
    )

print(result)

Schema

Input

callback_url · string (uri)

The callback notification address. Server will notify when the task status changes.

Format: uri

input · object | object | object | object | object | object · required

input.audio_file · string

Local Path of Audio File. Supported formats: .mp3/.wav/.m4a/.aac, maximum file size of 5MB. Base64 code.

input.audio_type · string

Method of Transmitting Audio Files for Lip-Sync. Required when mode is audio2video.

Possible values: file, url

input.audio_url · string

Audio File Download URL. Supported formats: .mp3/.wav/.m4a/.aac, maximum file size of 5MB.

input.mode · string · required

Video Generation Mode. text2video: Text-to-video generation mode; audio2video: Audio-to-video generation mode

Possible values: text2video, audio2video

input.text · string

Text Content for Lip-Sync Video Generation. Required when mode is text2video. Maximum length is 120 characters.

input.video_id · string

The ID of the video generated by Kling AI. Only supports 5-second and 10-second videos generated within the last 30 days.

input.video_url · string

Get link for uploaded video. Video files support .mp4/.mov, file size does not exceed 100MB, video length between 2-10s.

input.voice_id · string

Voice ID. Required when mode is text2video. The system offers a variety of voice options to choose from.

input.voice_language · string · default: "\"en\""

The voice language corresponds to the Voice ID.

Possible values: zh, en

input.voice_speed · number · default: "1"

Speech Rate. Valid range: 0.8~2.0, accurate to one decimal place.

Range: 0.8 to 2

Generated from the schema Router serves at GET /v2/models/kling/videos-lip-sync/openapi.json, the same document it validates a call against before the request reaches the provider.

Output

Router does not publish an output schema for this model.

Examples

Input

{
  "input": {
    "mode": "text2video",
    "text": "Welcome to Comfy Cloud.",
    "video_id": "kling-video-6f5e4d3c2b1a",
    "voice_id": "genshin_vindi2",
    "voice_language": "en",
    "voice_speed": 1
  }
}

Before you ship

The snippets above are the shortest working call. Three things are the same for every model and are documented once on the Comfy Router headers page: send an Idempotency-Key on every paid call and reuse it when you retry, expect the connection to be held up to Router’s 10 minute deadline, and keep X-Comfy-Request-Id from every response. The SDKs do all three for you; the cURL tab does none of them. On failure, X-Comfy-Error-Type names the bucket, and a 422 means the body failed the model’s schema and was never billed.

Headers

Authentication, idempotency, request IDs, error buckets, retry pacing, spend limits.

Quick Start

Typed error handling in Python and TypeScript, reading the 422, walking the catalog.

Limitations

What Router does not do today, and what to use instead.