> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mediamonster.app/llms.txt
> Use this file to discover all available pages before exploring further.

# Generators

> Make an image, a clip, a voice, or music from a prompt. Each model is its own price.

Generators make a new file from a prompt. Image and video generation can also take a file and start from it — a reference picture, or the first frame of a clip. Voice and music take no file and **must open the line**.

Each model is listed as its own skill page. Leave `model` off to use the default.

<Frame caption="Make an image. Default model is Gemini 2.5 Flash Image at 6 credits. Shape and size sit on the step.">
  <img src="https://mintcdn.com/mediamonster/KWUnAiqqRakm6EQT/images/screenshots/skill-generate.png?fit=max&auto=format&n=KWUnAiqqRakm6EQT&q=85&s=6707a4649d0d6eff41e126f6b10f6aa3" alt="Signed-in Workbench with Gemini 2.5 Flash Image on the line and Make 1 picture for 6 credits" width="1440" height="900" decoding="async" loading="lazy" data-path="images/screenshots/skill-generate.png" />
</Frame>

| Slug            | Takes | Credits          | Options               |
| --------------- | ----- | ---------------- | --------------------- |
| `generate`      | image | 5–20 per file    | model, shape, size    |
| `text-to-video` | image | 100–340 per file | model, length, shape  |
| `text-to-voice` | none  | 4–25 per minute  | model, voice, format  |
| `music`         | none  | 4–100 per minute | model, length, format |

## Make an image

Slug: `generate`. Default **6 credits** / image.

| Model id          | Name                   | Credits |
| ----------------- | ---------------------- | ------- |
| `nano-banana`     | Gemini 2.5 Flash Image | 6       |
| `nano-banana-pro` | Gemini 3 Pro Image     | 20      |
| `seedream-5-lite` | Seedream 5 Lite        | 6       |
| `qwen-image-3`    | Qwen Image 3           | 5       |

## Text to video

Slug: `text-to-video`. Default **100 credits** / clip.

| Model id       | Name         | Credits |
| -------------- | ------------ | ------- |
| `veo-3.1-lite` | Veo 3.1 Lite | 100     |
| `veo-3.1-fast` | Veo 3.1 Fast | 300     |
| `kling-3-pro`  | Kling 3 Pro  | 340     |
| `wan-3`        | Wan 3        | 200     |

## Text to voice

Slug: `text-to-voice`. Default **4 credits** / minute.

<Frame caption="Text to voice takes no file and must open the line.">
  <img src="https://mintcdn.com/mediamonster/KWUnAiqqRakm6EQT/images/screenshots/skill-text-to-voice.png?fit=max&auto=format&n=KWUnAiqqRakm6EQT&q=85&s=6d35de991c930ca2ac4fc77174ab541e" alt="Signed-in Workbench with Inworld TTS on the line and Make 1 track for 4 credits" width="1440" height="900" decoding="async" loading="lazy" data-path="images/screenshots/skill-text-to-voice.png" />
</Frame>

| Model id           | Name                 | Credits |
| ------------------ | -------------------- | ------- |
| `inworld`          | Inworld TTS          | 4       |
| `gemini-flash-tts` | Gemini 3.1 Flash TTS | 12      |
| `eleven-v3`        | ElevenLabs v3        | 25      |

## Make music

Slug: `music`. Default **12 credits** / minute.

| Model id           | Name             | Credits |
| ------------------ | ---------------- | ------- |
| `stable-audio-2.5` | Stable Audio 2.5 | 12      |
| `stable-audio-3`   | Stable Audio 3   | 4       |
| `eleven-music`     | ElevenLabs Music | 100     |

## From the API

Send a `prompt`, and optionally a `model`. Image and video generation also take a file or `url`.

```bash theme={"theme":{"light":"github-dark","dark":"github-dark"}}
curl -X POST https://mediamonster.app/api/v1/run/generate \
  -H "Authorization: Bearer mm_live_…" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "a studio product shot of a lime sneaker on paper", "model": "nano-banana"}'
```

See [Run a skill](/api/run-skill). Prompts are capped at 2,000 characters.