> ## 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.

# Music & Sound Effects Models

> Venice music and audio models for songs, instrumental tracks, and sound effects, including ElevenLabs Music, Lyria 3 Pro, and MiniMax Music.

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="ModelExplorer" modality="audio" task="music">
  <div id="model-catalog-static">
    Use the `id` value as the `model` parameter in API requests. 18 models currently available.

    | Model | ID | Pricing | Privacy |
    | - | - | - | - |
    | [ACE-Step 1.5](/models/ace-step-1-5) | `ace-step-15` | Duration-tiered — use Audio Quote API | Anonymized |
    | [ElevenLabs Multilingual v2](/models/elevenlabs-multilingual-v2) | `elevenlabs-tts-multilingual-v2` | See Audio Quote API | Anonymized |
    | [ElevenLabs Music](/models/elevenlabs-music) | `elevenlabs-music` | Duration-tiered — use Audio Quote API | Anonymized |
    | [ElevenLabs Music v2](/models/elevenlabs-music-v2) | `elevenlabs-music-v2` | Duration-tiered — use Audio Quote API | Anonymized |
    | [ElevenLabs Music v2.5](/models/elevenlabs-music-v2-5) | `elevenlabs-music-v2-5` | Duration-tiered — use Audio Quote API | Anonymized |
    | [ElevenLabs Sound Effects](/models/elevenlabs-sound-effects) | `elevenlabs-sound-effects-v2` | \$0.0023 / second | Anonymized |
    | [ElevenLabs TTS v3](/models/elevenlabs-tts-v3) | `elevenlabs-tts-v3` | See Audio Quote API | Anonymized |
    | ElevenLabs TTS v4 | `elevenlabs-tts-v4` | See Audio Quote API | Anonymized |
    | ElevenLabs TTS v4 Turbo | `elevenlabs-tts-v4-turbo` | See Audio Quote API | Anonymized |
    | [Lyria 3 Pro](/models/lyria-3-pro) | `lyria-3-pro` | \$0.10 / generation | Anonymized |
    | [MiniMax Music 2.0](/models/minimax-music-2-0) | `minimax-music-v2` | \$0.04 / generation | Anonymized |
    | [MiniMax Music 2.5](/models/minimax-music-2-5) | `minimax-music-v25` | \$0.18 / generation | Anonymized |
    | [MiniMax Music 2.6](/models/minimax-music-2-6) | `minimax-music-v26` | \$0.18 / generation | Anonymized |
    | [MMAudio V2](/models/mmaudio-v2) | `mmaudio-v2-text-to-audio` | \$0.0009 / second | Anonymized |
    | [Seed Audio 1.0](/models/seed-audio-1-0) | `seed-audio-1-0` | \$0.0029 / second | Anonymized |
    | [Sonilo V1.1 Music](/models/sonilo-v1-1-music) | `sonilo-v1-1-music` | \$0.0029 / second | Anonymized |
    | [Sonilo V1.1 Sound Effects](/models/sonilo-v1-1-sound-effects) | `sonilo-v1-1-sound-effects` | \$0.0021 / second | Anonymized |
    | [Stable Audio 2.5](/models/stable-audio-2-5) | `stable-audio-25` | \$0.19 / generation | Anonymized |
  </div>
</HubMount>

<div className="vx-prose">
  ## Model Categories

  **Song Generation:** Create full songs with optional lyrics and vocal support

  * ACE-Step 1.5, ElevenLabs Music, MiniMax Music 2.0

  **Music & Sound Effects:** Generate instrumental music or sound effects from text prompts

  * Stable Audio 2.5

  **Sound Effects:** Synthesize audio effects and ambient sounds from text prompts

  * ElevenLabs Sound Effects, MMAudio V2

  <Tip>
    `force_instrumental` generates music without vocals. It is supported by ElevenLabs Music, MiniMax Music 2.5, and MiniMax Music 2.6 — check `supports_force_instrumental` in the `/models` response rather than assuming a single model.
  </Tip>

  <Note>
    Audio generation uses an async queue system. Follow the [Music & Sound Effects guide](/guides/media/music-and-sound-effects) for a complete walkthrough, or see the [Audio Queue API](/api-reference/endpoint/audio/queue) to start generation and [Audio Retrieve API](/api-reference/endpoint/audio/retrieve) to fetch results. Models with `model_spec.voice_changer` set to `true` use the [Voice Changer](/guides/media/voice-changer) endpoints instead.
  </Note>

  ## Pricing

  Pricing varies by model:

  * **Per-generation:** Fixed price per audio clip (MiniMax Music 2.0, Stable Audio 2.5)
  * **Duration-tiered:** Price scales with duration tier (ElevenLabs Music, ACE-Step 1.5)
  * **Per-second:** Price based on output duration (ElevenLabs Sound Effects, MMAudio V2)

  For exact quotes before generation, use the [Audio Quote API](/api-reference/endpoint/audio/quote).

  ### Duration-Tiered Pricing

  Models with duration-tiered pricing accept any `duration_seconds` within the model's `min_duration`–`max_duration` range, **unless** the model also reports `duration_options` — in that case only those exact values are accepted and anything else returns a `400`. ACE-Step 1.5, for example, accepts only `60`, `90`, `120`, `150`, `180`, and `210`, so `duration_seconds: 75` is rejected even though it sits inside the advertised range. Always check `duration_options` before falling back to `min_duration`/`max_duration`.

  The price is determined by which tier the requested duration falls into. Tier ranges are returned in the `/models` response under `pricing.durations`, with `min_seconds` and `max_seconds` for each tier.

  For example, ElevenLabs Music accepts 3–600 seconds (up to 10 minutes) at \$0.75 per minute, rounded up to the nearest minute:

  | Duration Range | Tier Key | Base Price |
  | - | - | - |
  | 3–60s | `60` | \$0.75 |
  | 61–120s | `120` | \$1.50 |
  | 121–180s | `180` | \$2.25 |
  | 181–240s | `240` | \$3.00 |
  | 241–300s | `300` | \$3.75 |
  | 301–360s | `360` | \$4.50 |
  | 361–420s | `420` | \$5.25 |
  | 421–480s | `480` | \$6.00 |
  | 481–540s | `540` | \$6.75 |
  | 541–600s | `600` | \$7.50 |

  These are base prices before markup. Use the [Audio Quote API](/api-reference/endpoint/audio/quote) to get the exact price you will be charged.

  ## Key Parameters

  | Parameter | Description |
  | - | - |
  | `prompt` | Text description of the audio to generate |
  | `lyrics_prompt` | Song lyrics for vocal models (required when model has `lyrics_required=true`) |
  | `duration_seconds` | Output length in seconds |
  | `force_instrumental` | Generate without vocals (where supported) |
</div>


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