> ## Documentation Index
> Fetch the complete documentation index at: https://veniceai-mintlify-ce69695c.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.

<div id="model-search-placeholder" data-filter="music">
  Use the `id` value as the `model` parameter in API requests. 16 models currently available.

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

## 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) |


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