> ## Documentation Index
> Fetch the complete documentation index at: https://veniceai-feat-models-redesign.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# MMAudio V2 API

> MMAudio V2 API on Venice: sound effects, $0.055 per minute of audio. Anonymized access without your identity. Pricing, specs and code examples.

export const HubMount = ({view, children, ...props}) => {
  const [hub, setHub] = useState(null);
  const [failed, setFailed] = useState(false);
  useEffect(() => {
    let alive = true;
    const w = window;
    if (!w.__veniceModelHub) {
      const urls = w.location.hostname === 'localhost' ? ['http://localhost:3333/data/model-hub.bundle.json', '/data/model-hub.bundle.json'] : ['/data/model-hub.bundle.json'];
      const load = i => fetch(urls[i], {
        cache: 'no-cache'
      }).then(res => {
        if (!res.ok) throw new Error(`bundle ${res.status}`);
        return res.json();
      }).catch(err => i + 1 < urls.length ? load(i + 1) : Promise.reject(err));
      const Frag = <></>.type;
      const h = (type, props, ...kids) => {
        const T = type;
        const {key, ...rest} = props || ({});
        if (!kids.length) return <T key={key} {...rest} />;
        if (kids.length === 1) return <T key={key} {...rest}>{kids[0]}</T>;
        return <T key={key} {...rest}>{kids.map((kid, i) => <Frag key={i}>{kid}</Frag>)}</T>;
      };
      w.__veniceModelHub = load(0).then(bundle => new Function(`return (${bundle.code})`)()({
        h,
        Fragment: Frag,
        useState,
        useEffect,
        useRef,
        useMemo,
        useCallback
      }));
    }
    w.__veniceModelHub.then(instance => {
      if (alive) setHub(instance);
    }).catch(() => {
      w.__veniceModelHub = null;
      if (alive) setFailed(true);
    });
    return () => {
      alive = false;
    };
  }, []);
  const View = hub ? hub[view] : null;
  if (View) return <View {...props}>{children}</View>;
  if (failed) {
    return <div className="vx-mount is-failed">
        <p className="vx-mount-note">The interactive model catalog could not load. The full data is below.</p>
        {children}
      </div>;
  }
  return <div className="vx-mount" aria-busy="true">
      <div className="vx-mount-skeleton" aria-hidden="true"><span /><span /><span /></div>
      <div className="vx-mount-source">{children}</div>
    </div>;
};

<HubMount view="ModelPage" data={{"family":{"slug":"mmaudio-v2","name":"MMAudio V2","modality":"audio","task":"sfx","provider":"mmaudio","description":"Generate synchronized audio and sound effects from text prompts with MMAudio V2.","primary":"mmaudio-v2-text-to-audio","variants":["mmaudio-v2-text-to-audio"],"created":1772236800,"updated":1772236800,"privacy":["anonymized"]},"models":[{"id":"mmaudio-v2-text-to-audio","name":"MMAudio V2","type":"music","modality":"audio","task":"sfx","variant":"standard","provider":"mmaudio","created":1772236800,"description":"Generate synchronized audio and sound effects from text prompts with MMAudio V2.","privacy":"anonymized","audio":{"minDuration":1,"maxDuration":30,"defaultDuration":5,"formats":["wav"],"promptLimit":500},"pricing":{"kind":"per-second","perSecond":0.00092,"perMinute":0.0552},"headline":{"value":0.0552,"unit":"per minute of audio","basis":"minute"},"endpoints":[{"id":"audio-queue","method":"POST","path":"/audio/queue","name":"Queue generation","status":"stable","recommended":true},{"id":"audio-retrieve","method":"POST","path":"/audio/retrieve","name":"Retrieve result","status":"stable"},{"id":"audio-quote","method":"POST","path":"/audio/quote","name":"Quote price","status":"stable"}],"family":"mmaudio-v2"}],"related":{"similar":[{"slug":"elevenlabs-sound-effects","name":"ElevenLabs Sound Effects","provider":"elevenlabs","modality":"audio","privacy":["anonymized"],"created":1772236800,"headline":{"value":0.138,"unit":"per minute of audio","basis":"minute"},"variants":1},{"slug":"sonilo-v1-1-sound-effects","name":"Sonilo V1.1 Sound Effects","provider":"sonilo","modality":"audio","privacy":["anonymized"],"created":1784592000,"headline":{"value":0.1242,"unit":"per minute of audio","basis":"minute"},"variants":1}],"versions":[]},"providers":{"mmaudio":{"slug":"mmaudio","name":"MMAudio","logo":"/images/icons/models/music.svg","inferred":true},"elevenlabs":{"slug":"elevenlabs","name":"ElevenLabs","logo":"/images/icons/models/elevenlabs.svg"},"sonilo":{"slug":"sonilo","name":"Sonilo","logo":"/images/icons/models/music.svg","inferred":true}},"faq":[{"q":"How much does the MMAudio V2 API cost?","a":"$0.055 per minute of generated audio. Prices are in USD and can be paid in DIEM at parity."},{"q":"What is the MMAudio V2 model ID?","a":"Use `mmaudio-v2-text-to-audio` as the `model` parameter."},{"q":"Is the MMAudio V2 API private?","a":"MMAudio V2 is anonymized: Venice forwards requests to the provider without your identity, but the provider may retain prompt data, so use a private model for sensitive work."},{"q":"Which endpoint does the MMAudio V2 API use?","a":"Queue a job with `POST /audio/queue`, then poll `/audio/retrieve` for the result."}]}} />

<div className="vx-static">
  <Accordion title="Plain-text specification">
    # MMAudio V2 API

    MMAudio V2 is a sound effects model by MMAudio, available on the Venice API as `mmaudio-v2-text-to-audio`. Requests are anonymized, so the provider never sees your identity.

    Generate synchronized audio and sound effects from text prompts with MMAudio V2.

    ## MMAudio V2 API pricing

    | Model ID | Variant | Privacy | Price |
    | - | - | - | - |
    | `mmaudio-v2-text-to-audio` | Standard | Anonymized | \$0.06 per minute of audio |

    ## MMAudio V2 specifications

    | Spec | Value |
    | - | - |
    | Provider | MMAudio |
    | Released | Feb 28, 2026 |
    | Privacy | Anonymized |

    ## How to use the MMAudio V2 API

    Send requests to `POST https://api.venice.ai/api/v1/audio/queue` with `"model": "mmaudio-v2-text-to-audio"` and your API key.

    ```bash theme={null}
    # 1. Queue the job
    curl https://api.venice.ai/api/v1/audio/queue \
      -H "Authorization: Bearer $VENICE_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "mmaudio-v2-text-to-audio",
        "prompt": "Heavy wooden door creaking open in a stone hallway",
        "duration_seconds": 5
      }'

    # 2. Retrieve when ready
    curl https://api.venice.ai/api/v1/audio/retrieve \
      -H "Authorization: Bearer $VENICE_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{ "model": "mmaudio-v2-text-to-audio", "queue_id": "<queue_id>" }' --output audio.mp3
    ```

    ## MMAudio V2 API FAQ

    ### How much does the MMAudio V2 API cost?

    \$0.055 per minute of generated audio. Prices are in USD and can be paid in DIEM at parity.

    ### What is the MMAudio V2 model ID?

    Use `mmaudio-v2-text-to-audio` as the `model` parameter.

    ### Is the MMAudio V2 API private?

    MMAudio V2 is anonymized: Venice forwards requests to the provider without your identity, but the provider may retain prompt data, so use a private model for sensitive work.

    ### Which endpoint does the MMAudio V2 API use?

    Queue a job with `POST /audio/queue`, then poll `/audio/retrieve` for the result.

    ## Related models

    * [ElevenLabs Sound Effects API](/models/elevenlabs-sound-effects): \$0.14 per minute of audio
    * [Sonilo V1.1 Sound Effects API](/models/sonilo-v1-1-sound-effects): \$0.12 per minute of audio
  </Accordion>
</div>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.