founderfeed/multi-model-lipsync

Public

3 runs

Run founderfeed/multi-model-lipsync with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field	Type	Default value	Description
model	None	sync-lipsync-2-pro	Select the lipsync model to use
audio	string		Input audio file (MP3, WAV, etc.)
image	string		Input image (required for image2video models)
video	string		Input video (required for video2video models)
duration	integer		Video duration in seconds (4-10 for WAN 2.5 only)
voice_id	string	en_AOT	Voice ID for TTS (Kling only; used with text)
audio_text	string		Spoken content for lipsync (Kling if no audio; Veo required; WAN 2.5 if no audio).
resolution	string		Video resolution (e.g., 480p, 720p, 1080p for WAN 2.5, Veo models)
voice_speed	number	1 Min: 0.8 Max: 2	Voice speed for TTS (Kling only; used with text)
aspect_ratio	string		Video aspect ratio (e.g., 16:9, 9:16 for Veo models only)
replicate_api_key	string		Your Replicate API key (starts with r8_). SECURITY: This key is automatically secured and never logged or exposed in outputs.

{
  "type": "object",
  "title": "Input",
  "required": [
    "replicate_api_key"
  ],
  "properties": {
    "audio": {
      "type": "string",
      "title": "Audio",
      "format": "uri",
      "nullable": true,
      "description": "Input audio file (MP3, WAV, etc.)"
    },
    "image": {
      "type": "string",
      "title": "Image",
      "format": "uri",
      "nullable": true,
      "description": "Input image (required for image2video models)"
    },
    "model": {
      "enum": [
        "bytedance-omni-human",
        "wan-video-wan-2.5-i2v",
        "google-veo-3",
        "google-veo-3-fast",
        "pixverse-lipsync",
        "sync-lipsync-2-pro",
        "kling-lip-sync"
      ],
      "type": "string",
      "title": "model",
      "description": "Select the lipsync model to use",
      "default": "sync-lipsync-2-pro",
      "x-order": 1
    },
    "video": {
      "type": "string",
      "title": "Video",
      "format": "uri",
      "nullable": true,
      "description": "Input video (required for video2video models)"
    },
    "duration": {
      "type": "integer",
      "title": "Duration",
      "nullable": true,
      "description": "Video duration in seconds (4-10 for WAN 2.5 only)"
    },
    "voice_id": {
      "type": "string",
      "title": "Voice Id",
      "default": "en_AOT",
      "description": "Voice ID for TTS (Kling only; used with text)"
    },
    "audio_text": {
      "type": "string",
      "title": "Audio Text",
      "nullable": true,
      "description": "Spoken content for lipsync (Kling if no audio; Veo required; WAN 2.5 if no audio)."
    },
    "resolution": {
      "type": "string",
      "title": "Resolution",
      "nullable": true,
      "description": "Video resolution (e.g., 480p, 720p, 1080p for WAN 2.5, Veo models)"
    },
    "voice_speed": {
      "type": "number",
      "title": "Voice Speed",
      "default": 1,
      "maximum": 2,
      "minimum": 0.8,
      "description": "Voice speed for TTS (Kling only; used with text)"
    },
    "aspect_ratio": {
      "type": "string",
      "title": "Aspect Ratio",
      "nullable": true,
      "description": "Video aspect ratio (e.g., 16:9, 9:16 for Veo models only)"
    },
    "replicate_api_key": {
      "type": "string",
      "title": "Replicate Api Key",
      "format": "password",
      "writeOnly": true,
      "description": "Your Replicate API key (starts with r8_). SECURITY: This key is automatically secured and never logged or exposed in outputs.",
      "x-cog-secret": true
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "string",
  "title": "Output",
  "format": "uri"
}