Video

MMAudio v2

Credit-based pricing. Supports reference video.

Try MMAudio v2 →Compare models

Output

video

Inputs

Reference video (required)

Example prompt

Upload a silent video and describe the audio — MMAudio v2 generates precisely synced sound effects and ambient audio that match every visual detail

Try this prompt →

LLM-ready

API & LLM schema

Exact request contract for this model. Agents can fetch it from /api/v1/models?id=fal-ai/mmaudio-v2.

POST/api/v1/generate14 fields · 3 required

Field	Type	Requirement	Contract
`model_id`	constant	Required	ArtEmotion model identifier.
`extra`	object	Optional	Model-specific settings may also be nested here.
`max_credits`	number	Optional	Reject before submission if the estimated list price exceeds this cap. · Range: 1–…
`webhook_url`	string	Optional	Format: uri
`webhook_secret`	string	Optional	Optional model input.
`folder_id`	string	Optional	Optional model input.
`prompt`	string	Required	Optional model input.
`duration`	number	Optional	Duration of the audio to generate in seconds. · Default: 8 · Range: 1–30
`num_steps`	number	Optional	Number of diffusion steps (more = higher quality but slower). · Default: 25 · Range: 4–50
`cfg_strength`	number	Optional	Classifier-free guidance strength. · Default: 4.5 · Range: 0–20
`negative_prompt`	string	Optional	Audio characteristics to avoid. · Default:
`mask_away_clip`	boolean	Optional	Disable the CLIP visual stream (text-driven mode only). · Default: false
`seed`	integer	Optional	Seed for reproducibility. · Range: 0–65535
`video_url`	string	Required	Format: uri

Minimal request example

{
  "model_id": "fal-ai/mmaudio-v2",
  "prompt": "Upload a silent video and describe the audio — MMAudio v2 generates precisely synced sound effects and ambient audio that match every visual detail",
  "video_url": "https://example.com/video"
}

Raw JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://www.artemotion.ai/api/v1/models?id=fal-ai%2Fmmaudio-v2",
  "title": "MMAudio v2 generation request",
  "description": "Request body accepted by POST /api/v1/generate for fal-ai/mmaudio-v2.",
  "type": "object",
  "properties": {
    "model_id": {
      "type": "string",
      "const": "fal-ai/mmaudio-v2",
      "description": "ArtEmotion model identifier."
    },
    "extra": {
      "type": "object",
      "additionalProperties": true,
      "description": "Model-specific settings may also be nested here."
    },
    "max_credits": {
      "type": "number",
      "minimum": 1,
      "description": "Reject before submission if the estimated list price exceeds this cap."
    },
    "webhook_url": {
      "type": "string",
      "format": "uri",
      "maxLength": 2048
    },
    "webhook_secret": {
      "type": "string",
      "maxLength": 512
    },
    "folder_id": {
      "type": "string"
    },
    "prompt": {
      "type": "string"
    },
    "duration": {
      "title": "Duration",
      "description": "Duration of the audio to generate in seconds.",
      "default": 8,
      "type": "number",
      "minimum": 1,
      "maximum": 30
    },
    "num_steps": {
      "title": "Num Steps",
      "description": "Number of diffusion steps (more = higher quality but slower).",
      "default": 25,
      "type": "number",
      "minimum": 4,
      "maximum": 50,
      "multipleOf": 1
    },
    "cfg_strength": {
      "title": "CFG Strength",
      "description": "Classifier-free guidance strength.",
      "default": 4.5,
      "type": "number",
      "minimum": 0,
      "maximum": 20
    },
    "negative_prompt": {
      "title": "Negative Prompt",
      "description": "Audio characteristics to avoid.",
      "default": "",
      "type": "string"
    },
    "mask_away_clip": {
      "title": "Mask Away Clip",
      "description": "Disable the CLIP visual stream (text-driven mode only).",
      "default": false,
      "type": "boolean"
    },
    "seed": {
      "title": "Seed",
      "description": "Seed for reproducibility.",
      "type": "integer",
      "minimum": 0,
      "maximum": 65535
    },
    "video_url": {
      "type": "string",
      "format": "uri"
    }
  },
  "required": [
    "model_id",
    "prompt",
    "video_url"
  ],
  "additionalProperties": false
}

Browse schemas for every ArtEmotion model →

FAQ

How much does MMAudio v2 cost on ArtEmotion?

Credit-based pricing. You pay in ArtEmotion credits — every plan and top-up converts USD to credits at a fixed rate.

Do I get my credits back if MMAudio v2 fails?

Yes — failed generations are never charged. The credits are released back to your balance automatically.

Can I call MMAudio v2 from the API?

Yes. Use POST /api/v1/generate with model_id: "fal-ai/mmaudio-v2". See the API reference for the full schema.

Where are my generations stored?

Every output is saved to your personal Library. You can export or delete everything any time from Privacy & deletion.

Ready to generate with MMAudio v2?

Start now →

No commitment. New accounts get 50 free credits on signup. See pricing.