# Mirelo SFX 2.0 MCP and API - Sound effects by Mirelo | FlyMy.AI

> Mirelo SFX 2.0 generates sound effects and ambience from a text description, from one second to ten minutes, in up to four variations at once.

Page: https://flymy.ai/mcp/models/mirelo-sfx-2-0-text-to-audio/

MCP / Models / Voice, music and sound

# Mirelo SFX 2.0 MCP: sound effects from text with no API key

Mirelo SFX 2.0 generates sound effects and ambience from a text description, from one second to ten minutes, in up to four variations at once. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

[Use Mirelo SFX 2.0](https://flymy.ai/mcp/models/mirelo-sfx-2-0-text-to-audio/#start) [Inputs and price](https://flymy.ai/mcp/models/mirelo-sfx-2-0-text-to-audio/#inputs)

No API key, $0.015 / s, Sound effects, Mirelo, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## Use Mirelo SFX 2.0 in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

```
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/mirelo-sfx-2-0-text-to-audio.md. Help me connect the FlyMy.AI MCP to this assistant, then run Mirelo SFX 2.0 (flymyai/mirelo-sfx-2_0-text-to-audio) for this task: Make 20 seconds of rain on a metal roof with Mirelo SFX 2.0.
```

[Open FlyMy.AI](https://app.flymy.ai/new-agent) [Download brief](https://flymy.ai/mcp/models/mirelo-sfx-2-0-text-to-audio.md)

## What Mirelo SFX 2.0 does

Describe the sound in prompt, up to 2,000 characters, and what to keep out in negative_prompt, such as music or voices. duration sets the length in whole seconds from 1 to 600 (10 by default), num_samples asks for one to four variations, seed repeats a result and upload_audio_format picks WAV, MP3, AAC or FLAC. Output: audio, one file per variation. It does not watch a video (Mirelo SFX 2.0 Video to Audio does) and makes no music or speech.

Guide: [Songs, instrumentals and sound effects through the API](https://flymy.ai/blog/ai-3d-model-generator-api/)

## Mirelo SFX 2.0 inputs

Every input of `flymyai/mirelo-sfx-2_0-text-to-audio` as its live schema lists them. Returns `audio` (array).

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/mirelo-sfx-2-0-text-to-audio/#input-prompt) `prompt` | string required What the sound should be, up to 2000 characters, e.g. heavy rain on a metal roof with distant thunder |
| [#](https://flymy.ai/mcp/models/mirelo-sfx-2-0-text-to-audio/#input-negative_prompt) `negative_prompt` | string optional Sounds to keep out, e.g. music, voices (up to 1000 characters) |
| [#](https://flymy.ai/mcp/models/mirelo-sfx-2-0-text-to-audio/#input-duration) `duration` | integer optional Allowed: 1 to 600 Default: `10` Length in whole seconds, 1-600; $0.015 per second for each variation |
| [#](https://flymy.ai/mcp/models/mirelo-sfx-2-0-text-to-audio/#input-num_samples) `num_samples` | integer optional Allowed: 1 to 4 Default: `1` How many variations of the sound, 1-4; each one is billed |
| [#](https://flymy.ai/mcp/models/mirelo-sfx-2-0-text-to-audio/#input-seed) `seed` | integer optional Allowed: 0 to 2147483647 Seed of the first variation; the same seed repeats a result |
| [#](https://flymy.ai/mcp/models/mirelo-sfx-2-0-text-to-audio/#input-upload_audio_format) `upload_audio_format` | string optional Allowed: wav, mp3, aac, flac Default: `wav` File format: wav, mp3, aac or flac |

## Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

**“Make 20 seconds of rain on a metal roof with Mirelo SFX 2.0.”** runs `flymyai/mirelo-sfx-2_0-text-to-audio`

**“Use Mirelo SFX 2.0 to generate three variations of a heavy wooden door creaking open.”** runs `flymyai/mirelo-sfx-2_0-text-to-audio`

**“Create a busy city street ambience for a video scene with Mirelo SFX 2.0, with no music or voices.”** runs `flymyai/mirelo-sfx-2_0-text-to-audio`

## Mirelo SFX 2.0 price

$0.015 per second of duration. A run at the default settings costs $0.15. A run costs $0.015 to $36.00, depending on duration and num_samples. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

| Setting | Price |
|---|---|
| Any | $0.015 per second |

[See usage pricing →](https://flymy.ai/pricing/)

## Call Mirelo SFX 2.0 from code

The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.

### From an agent, through the MCP

The agent calls `get_model_schema`, then `run_model` with:

```
{
  "endpoint_id": "flymyai/mirelo-sfx-2_0-text-to-audio",
  "input": {
    "prompt": "Rain on a metal roof with distant thunder"
  }
}
```

### From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. The answer is a `prediction_id`; read the result at `https://api.flymy.ai/api/v1/flymyai/mirelo-sfx-2_0-text-to-audio/predict/async/result/?request_id=<prediction_id>`.

```
curl -X POST https://api.flymy.ai/api/v1/flymyai/mirelo-sfx-2_0-text-to-audio/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Rain on a metal roof with distant thunder'
```

## Questions about Mirelo SFX 2.0

**Do I need a Mirelo API key for Mirelo SFX 2.0?**

No. Mirelo SFX 2.0 runs on FlyMy.AI's account, so you need no Mirelo key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

**How much does Mirelo SFX 2.0 cost?**

$0.015 per second of duration. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.

**How do I use Mirelo SFX 2.0 in Claude Code, Codex or Cursor?**

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Make 20 seconds of rain on a metal roof with Mirelo SFX 2.0." Your agent reads the inputs with get_model_schema and runs flymyai/mirelo-sfx-2_0-text-to-audio with run_model.

**What does Mirelo SFX 2.0 need as input?**

Mirelo SFX 2.0 requires prompt; it also takes 5 optional inputs, each listed on this page with its allowed values and default.

**Can I call Mirelo SFX 2.0 from my own code?**

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/mirelo-sfx-2_0-text-to-audio/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

## More voice, music and sound models

Read text aloud, clone a voice from a short sample, turn lyrics or a prompt into a song, compose instrumentals, make sound effects from a description or for a video, or repair and extend a track.

### Mirelo SFX 2.0 Video to Audio

Foley and ambience made to fit your clip, returned as separate audio files.

Sound for video / from $0.015 / run

Link: https://flymy.ai/mcp/models/mirelo-sfx-2-0-video-to-audio/

### Mirelo SFX 2.0 Video to Video

A silent clip goes in, the same clip comes back with sound effects and ambience.

Sound for video / from $0.015 / run

Link: https://flymy.ai/mcp/models/mirelo-sfx-2-0-video-to-video/

### Gemini 3.8 Flash TTS

Google's higher-fidelity speech model: narration and multi-character scripts in 30 voices, with style control.

Text to speech / about $0.0135 / min of speech

Link: https://flymy.ai/mcp/models/gemini-3-8-flash-tts/

### Gemini 3.8 Flash-Lite TTS

The low-cost Gemini 3.8 speech model for high volume: read-aloud features and voice agents.

Text to speech / about $0.009 / min of speech

Link: https://flymy.ai/mcp/models/gemini-3-8-flash-lite-tts/

### Lyria 3.5

Google DeepMind's music model: full songs or instrumentals from a written brief.

Music / $0.10 / run

Link: https://flymy.ai/mcp/models/lyria-3-5-music/

### MiniMax Music 3

MiniMax's open-weights music model: lyrics and a style prompt in, a full song with vocals out.

Music / $0.002 / s

Link: https://flymy.ai/mcp/models/minimax-music-3/

## Go to the source

[Mirelo SFX 2.0 in the playground →](https://app.flymy.ai/models/flymyai/mirelo-sfx-2_0-text-to-audio), [Model endpoints in the docs →](https://docs.flymy.ai/api/models-endpoints), [Every model on FlyMy.AI →](https://flymy.ai/mcp/models/), [Every MCP in the catalog →](https://flymy.ai/mcp/#catalog), [Usage pricing →](https://flymy.ai/pricing/)

From the FlyMy.AI model catalog of 2026-11-18: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.

---

For agents: the FlyMyAI operating guide (sign up, connect, run models, tools and agents) is https://flymy.ai/skill.md, and https://flymy.ai/llms.txt lists the other pages and the documentation.
