--- title: Mirelo | Scenario Docs --- > This page is auto-generated from model configurations. Last updated: 2026-11-02. This reference lists all available **Mirelo** audio generation models and their parameters. Use these parameter names when calling the [Generation API](/api/postgeneratecustom/index.md). - [Mirelo SFX 2.0 Text to Audio](#mirelo-sfx-20-text-to-audio) - [Mirelo SFX 2.0 Video to Audio](#mirelo-sfx-20-video-to-audio) --- ## Mirelo SFX 2.0 Text to Audio Generate sound effects from a text prompt, with several variations per run and control over duration **Model ID:** `model_mirelo-sfx-2-0-text-to-audio` **Capabilities:** `txt2audio` **LLM Markdown:** | Parameter | Type | Required | Default | Min | Max | Allowed Values | Description | | ---------------- | ------ | -------- | ------- | --- | ---------- | --------------------------- | ------------------------------------------------------------------------------------------------------- | | `prompt` | string | Yes | - | - | - | - | Describe the sound you want to create — for example: ‘Heavy rain on a metal roof with distant thunder’. | | `negativePrompt` | string | No | - | - | - | - | Sounds to keep out of the result, as a short comma-separated list. | | `duration` | number | No | `30` | 0.1 | 600 | - | Length of each sound, in seconds. Longer sounds cost more. | | `numOutputs` | number | No | `2` | 1 | 4 | - | Number of variations to generate. Each variation is billed separately. | | `audioFormat` | string | No | `wav` | - | - | `wav`, `mp3`, `aac`, `flac` | Format of the returned audio files. | | `seed` | number | No | - | 0 | 2147483647 | - | Seed of the first variation, for reproducible results. Leave empty for a random seed. | ## Mirelo SFX 2.0 Video to Audio Generate a soundtrack synchronized to a video — sound effects with optional speech preservation — and return it as audio tracks **Model ID:** `model_mirelo-sfx-2-0-video-to-audio` **Capabilities:** `video2audio` **LLM Markdown:** | Parameter | Type | Required | Default | Min | Max | Allowed Values | Description | | ---------------- | ------- | -------- | ------- | --- | ---------- | --------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- | | `video` | file | Yes | - | - | - | - | The video to generate sound for. It must be at least 1 second long. Cost scales with the generated duration, which never exceeds the video length. | | `prompt` | string | No | - | - | - | - | Optional. Describe the kind of sound you want to guide the generation. | | `negativePrompt` | string | No | - | - | - | - | Sounds to keep out of the result, as a short comma-separated list. | | `preserveSpeech` | boolean | No | `true` | - | - | - | Keep the speech already in the video and generate the rest of the soundtrack around it. Turn off to generate sound effects only. | | `duration` | number | No | `10` | 1 | 600 | - | Seconds of sound to generate, clamped to the video length. Longer sounds cost more. | | `numOutputs` | number | No | `2` | 1 | 4 | - | Number of variations to generate. Each variation is billed separately. | | `audioFormat` | string | No | `wav` | - | - | `wav`, `mp3`, `aac`, `flac` | Format of the returned audio files. | | `seed` | number | No | - | 0 | 2147483647 | - | Seed for reproducible results. Leave empty for a random seed. |