# MMAudio V2

> Add realistic, synchronized sound effects, Foley, ambience, or music to a silent video from a text prompt, returning the video with a new audio track.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/mmaudio/v2`
- **Model ID**: `mmaudio/v2`
- **Category**: video-to-video
- **Kind**: inference
- **Tags**: mmaudio, video-to-audio, video-to-video, foley, sound-effects, sound-design

## Pricing

- **Price**: $0.001 per output second

## Request Lifecycle

This model runs on the ModelRunner **asynchronous queue API** — a single POST does not return the output. Every call requires an `Authorization: Key $MODEL_RUNNER_KEY` header. Run three steps:

1. **Submit** — `POST https://queue.modelrunner.run/mmaudio/v2` with a JSON body holding the input fields at the top level. The body may also include a reserved top-level `metadata` object — a flat string map (max 16 keys, key ≤64 / value ≤512 chars) stored on the request for your own tagging. It is never sent to the model; filter your request history with `GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>` (exact key=value matches, AND-ed). The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/mmaudio/v2/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/mmaudio/v2/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/mmaudio/v2/requests/<request_id>/cancel"
}
```

2. **Poll status** — `GET <status_url>` until `status` is `COMPLETED`. Possible values are `IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`, `CANCELLED`. A `FAILED` request responds with HTTP 400 and an `error` field.

3. **Read result** — `GET <response_url>`. Returns the finished request, including the generated `output`:

```json
{ "id": "<request_id>", "status": "COMPLETED", "output": ..., "input": ... }
```

The JavaScript and Python SDKs below perform steps 2–3 for you. In any language without an SDK (Swift, Go, Kotlin, etc.) you must implement the polling loop and the final result fetch yourself — see the cURL example for the full flow.

### Input Schema

- **`seed`** (`integer | null`, _optional_):
  Random seed for reproducible generation. Leave unset for a random result.

- **`prompt`** (`string`, _required_):
  Text description of the sound to generate (sound effects, Foley, ambience, or music).

- **`duration`** (`number`, _optional_):
  Duration of the generated audio in seconds.
  - Default: `8`
  - Range: `1` to `30`

- **`num_steps`** (`integer`, _optional_):
  Number of diffusion inference steps.
  - Default: `25`
  - Range: `4` to `50`

- **`video_url`** (`string`, _required_):
  URL of the input video to add a generated audio track to.

- **`cfg_strength`** (`number`, _optional_):
  Classifier-free guidance strength; higher follows the prompt more strictly.
  - Default: `4.5`
  - Range: `0` to `20`

- **`mask_away_clip`** (`boolean`, _optional_):
  Whether to mask away the input video's visual conditioning during generation.
  - Default: `false`

- **`negative_prompt`** (`string`, _optional_):
  Audio characteristics to steer away from.
  - Default: `""`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "prompt": "thunderstorm with heavy rain and distant rumbling thunder",
  "duration": 8,
  "num_steps": 25,
  "video_url": "https://media.modelrunner.ai/DzktjWqZAqCS1iWBKGhlm.mp4",
  "cfg_strength": 4.5,
  "mask_away_clip": false,
  "negative_prompt": ""
}
```

**Output**

```json
"https://media.modelrunner.ai/g7U4dexFgbppLmndAuYl1.mp4"
```
## Usage Examples

### cURL

The queue API is asynchronous: submit the request, poll `status_url` until it is `COMPLETED`, then read the result from `response_url`. Requires `jq`.

```bash
# 1. Submit the request (returns request handles, not the output)
SUBMIT=$(curl --silent --request POST \
  --url https://queue.modelrunner.run/mmaudio/v2 \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "thunderstorm with heavy rain and distant rumbling thunder",
  "duration": 8,
  "num_steps": 25,
  "video_url": "https://media.modelrunner.ai/DzktjWqZAqCS1iWBKGhlm.mp4",
  "cfg_strength": 4.5,
  "mask_away_clip": false,
  "negative_prompt": ""
}')

STATUS_URL=$(echo "$SUBMIT" | jq -r '.status_url')
RESPONSE_URL=$(echo "$SUBMIT" | jq -r '.response_url')

# 2. Poll until the request leaves the queue / in-progress state
while true; do
  STATUS=$(curl --silent --url "$STATUS_URL" \
    --header "Authorization: Key $MODEL_RUNNER_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  case "$STATUS" in
    COMPLETED) break ;;
    FAILED|CANCELLED) echo "Request $STATUS"; exit 1 ;;
  esac
  sleep 1
done

# 3. Read the finished request, including the generated output
curl --silent --url "$RESPONSE_URL" \
  --header "Authorization: Key $MODEL_RUNNER_KEY"
```

### JavaScript

```javascript
import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("mmaudio/v2", {
  input: {
  "prompt": "thunderstorm with heavy rain and distant rumbling thunder",
  "duration": 8,
  "num_steps": 25,
  "video_url": "https://media.modelrunner.ai/DzktjWqZAqCS1iWBKGhlm.mp4",
  "cfg_strength": 4.5,
  "mask_away_clip": false,
  "negative_prompt": ""
}
});

console.log(result.data);
```

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "mmaudio/v2",
        arguments={
  "prompt": "thunderstorm with heavy rain and distant rumbling thunder",
  "duration": 8,
  "num_steps": 25,
  "video_url": "https://media.modelrunner.ai/DzktjWqZAqCS1iWBKGhlm.mp4",
  "cfg_strength": 4.5,
  "mask_away_clip": false,
  "negative_prompt": ""
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/mmaudio/v2)
- [OpenAPI Schema](https://modelrunner.ai/models/mmaudio/v2/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/mmaudio/v2/llms.txt)