# Lyria 3.5 MCP and API - Music by Google | FlyMy.AI

> Google DeepMind's Lyria 3.5 composes a complete song, with sung lyrics or instrumental, from a text description, in eight languages.

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

MCP / Models / Voice, music and sound

# Lyria 3.5 MCP: songs from a text prompt with no API key

Google DeepMind's Lyria 3.5 composes a complete song, with sung lyrics or instrumental, from a text description, in eight languages. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

[Use Lyria 3.5](https://flymy.ai/mcp/models/lyria-3-5-music/#start) [Inputs and price](https://flymy.ai/mcp/models/lyria-3-5-music/#inputs)

No API key, $0.10 / run, Music, Google, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## Use Lyria 3.5 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/lyria-3-5-music.md. Help me connect the FlyMy.AI MCP to this assistant, then run Lyria 3.5 (flymyai/lyria-3_5-music) for this task: Write a short indie pop song about a summer road trip with Lyria 3.5, with a verse and a chorus.
```

[Open FlyMy.AI](https://app.flymy.ai/new-agent) [Download brief](https://flymy.ai/mcp/models/lyria-3-5-music.md)

## What Lyria 3.5 does

Put the genre, mood, instruments, tempo, vocals and structure into prompt, up to 5,000 characters; ask for a length with a hint such as a 2-minute track or with timed sections, and put the words to sing in quotes. An optional image sets the mood. Outputs: audio (MP3) and lyrics, the words it sang with the model's own section tags. It makes music only, not speech or sound effects, and takes no reference song.

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

## Lyria 3.5 inputs

Every input of `flymyai/lyria-3_5-music` as its live schema lists them. Returns `audio` (array), `lyrics` (string).

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/lyria-3-5-music/#input-prompt) `prompt` | string required Describe the song: genre, mood, instruments, tempo, vocals and structure; ask for a length ('a 2-minute track', timed sections) and put the words to sing in quotes; up to 5000 characters |
| [#](https://flymy.ai/mcp/models/lyria-3-5-music/#input-image) `image` | file optional Allowed: image file, as a URL or upload Optional picture whose mood and theme the music follows: a link or an upload |

## Ask your agent

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

**“Write a short indie pop song about a summer road trip with Lyria 3.5, with a verse and a chorus.”** runs `flymyai/lyria-3_5-music`

**“Use Lyria 3.5 to turn these lyrics into a slow acoustic ballad.”** runs `flymyai/lyria-3_5-music`

**“Make an upbeat jingle for noise-cancelling earbuds with Lyria 3.5.”** runs `flymyai/lyria-3_5-music`

## Lyria 3.5 price

$0.10 per run. A run at the default settings costs $0.10. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

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

## Call Lyria 3.5 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/lyria-3_5-music",
  "input": {
    "prompt": "Warm lo-fi beat with soft piano and light vinyl crackle"
  }
}
```

### 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/lyria-3_5-music/predict/async/result/?request_id=<prediction_id>`.

```
curl -X POST https://api.flymy.ai/api/v1/flymyai/lyria-3_5-music/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Warm lo-fi beat with soft piano and light vinyl crackle'
```

## Questions about Lyria 3.5

**Do I need a Google API key for Lyria 3.5?**

No. Lyria 3.5 runs on FlyMy.AI's account, so you need no Google key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

**How much does Lyria 3.5 cost?**

$0.10 per run. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.

**How do I use Lyria 3.5 in Claude Code, Codex or Cursor?**

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Write a short indie pop song about a summer road trip with Lyria 3.5, with a verse and a chorus." Your agent reads the inputs with get_model_schema and runs flymyai/lyria-3_5-music with run_model.

**What does Lyria 3.5 need as input?**

Lyria 3.5 requires prompt; it also takes 1 optional input, each listed on this page with its allowed values and default.

**Can I call Lyria 3.5 from my own code?**

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/lyria-3_5-music/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.

### 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/

### 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/

### MiniMax Speech 2.8 HD

MiniMax's high-quality speech model: 332 voices, 40 languages, emotions and laughs written into the text.

Text to speech / $0.10 / 1,000 characters

Link: https://flymy.ai/mcp/models/minimax-speech-2-8-hd/

### MiniMax Speech 2.8 Turbo

The faster, lower-priced MiniMax Speech 2.8: the same 332 voices and tags in the text, for speed and volume.

Text to speech / $0.06 / 1,000 characters

Link: https://flymy.ai/mcp/models/minimax-speech-2-8-turbo/

### Mirelo SFX 2.0

Foley, impacts and ambience from a sentence, up to four takes per request.

Sound effects / $0.015 / s

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

## Go to the source

[Lyria 3.5 in the playground →](https://app.flymy.ai/models/flymyai/lyria-3_5-music), [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.
