[Integrations](https://spiral.ai/integrations) › [Codex](https://spiral.ai/integrations/codex) › [Stable Audio 3 Medium Base Text to Audio](https://spiral.ai/integrations/codex/stable-audio-3-medium-base-text-to-audio)

# How to Use Stable Audio 3 Medium Base Text to Audio in Codex

Use Stable Audio 3 Medium Base Text to Audio to create instrumental music from written descriptions. Unlike Stable Audio 3 Medium Base Audio to Audio, it needs no recording to start.

|  |  |
| --- | --- |
| Model | Stable Audio 3 Medium Base Text to Audio |
| Available through | fal |
| Category | Audio |
| Price | $0.06227 per run at the default inputs. |
| Returns | audio |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Stable Audio 3 Medium Base Text to Audio in Codex

- Read the game's village scene notes and use Stable Audio 3 Medium Base Text to Audio to create a 45-second instrumental draft with acoustic guitar, soft flute, and a relaxed mood. Use 50 sampling steps.
- Read the product walkthrough script and use Stable Audio 3 Medium Base Text to Audio to make a 60-second instrumental cue with muted synth chords and restrained percussion. Save it as a draft for review.
- Use Stable Audio 3 Medium Base Text to Audio to create a 20-second instrumental title cue for this game: low strings, measured percussion, and a tense mood. Use 50 sampling steps and guidance 7.
- Compose a 30-second upbeat lo-fi track with Stable Audio 3 Medium Base Text to Audio for a product video. Save the result in ./assets.
- Make a calm piano loop with Stable Audio 3 Medium Base Text to Audio for a meditation app.

## How to set up Stable Audio 3 Medium Base Text to Audio in Codex

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the hosted server**

```bash
codex mcp add spiral --url https://api.spiral.ai/mcp
```

2. **Sign in**: Codex opens the browser: sign in to Spiral and click Authorize. No API key. `codex mcp list` then shows Spiral.

```bash
codex mcp login spiral
```

### Use the Spiral skill

1. **Send Codex this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Stable Audio 3 Medium Base Text to Audio**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/stable-audio-3/medium/base/text-to-audio",
    "input": {
      "prompt": "An anthemic Pop Rock instrumental that fills your head with nostalgic thoughtfulness"
    }
  }'
```

Then paste one of the prompts above: Codex finds Stable Audio 3 Medium Base Text to Audio on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/codex

## Stable Audio 3 Medium Base Text to Audio tools and prices

- [Stable Audio 3 Medium Base · Text to Audio](https://spiral.ai/tools/fal/fal-ai/stable-audio-3/medium/base/text-to-audio) (fal): $0.06227 per run at the default inputs.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| negative_prompt |  |  | Text description of qualities to avoid in the output. |
| duration | 1 to 380 | 30 | Duration of the generated audio in seconds. The medium model supports up to 380 seconds (~6m20s). |
| num_inference_steps | 1 to 100 | 50 | Number of sampling steps. Base (non-distilled) checkpoints typically need ~50 for good quality. |
| guidance_scale | 0 to 25 | 7 | Classifier-free guidance scale. Higher values follow the prompt more strictly; ~7.0 is a good starting point for base checkpoints. |
| seed |  | — | Random seed for reproducible outputs. Omit for a random seed. |
| enable_prompt_expansion |  | false | If True, the prompt will be expanded using an LLM for more detailed and higher quality results. |

## What can you do with Stable Audio 3 Medium Base Text to Audio in Codex?

Build instrumental audio drafts for game scenes, demos, and other project assets with Stable Audio 3 Medium Base. Use the project's creative brief to define the sound and review each result before adding it.

### Podcast background music

Create or restyle a restrained instrumental bed with sparse piano, soft bass, and room for narration.

### Product demo soundtracks

Develop a short instrumental cue for a walkthrough. Describe the instruments, pace, and energy the demonstration needs.

### Game scene music drafts

Explore instrumental directions for a quiet village, tense corridor, or victory scene before selecting music for the game.

### Short film score sketches

Draft a musical mood for a scene, using a written brief or an existing recording as the starting point.

### Composing from a written brief

Turn a description of genre, instrumentation, and mood into an instrumental draft without supplying a recording.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Codex guides](https://spiral.ai/integrations/codex)

## Stable Audio 3 Medium Base Text to Audio in other agents

- [Amp](https://spiral.ai/integrations/amp/stable-audio-3-medium-base-text-to-audio)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/stable-audio-3-medium-base-text-to-audio)
- [Claude](https://spiral.ai/integrations/claude-desktop/stable-audio-3-medium-base-text-to-audio)
- [Claude Code](https://spiral.ai/integrations/claude-code/stable-audio-3-medium-base-text-to-audio)
- [Cline](https://spiral.ai/integrations/cline/stable-audio-3-medium-base-text-to-audio)
- [Cursor](https://spiral.ai/integrations/cursor/stable-audio-3-medium-base-text-to-audio)
- [Devin](https://spiral.ai/integrations/devin/stable-audio-3-medium-base-text-to-audio)
- [dots](https://spiral.ai/integrations/dots/stable-audio-3-medium-base-text-to-audio)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/stable-audio-3-medium-base-text-to-audio)
- [Gemini](https://spiral.ai/integrations/gemini/stable-audio-3-medium-base-text-to-audio)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/stable-audio-3-medium-base-text-to-audio)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/stable-audio-3-medium-base-text-to-audio)
- [goose](https://spiral.ai/integrations/goose/stable-audio-3-medium-base-text-to-audio)
- [Grok](https://spiral.ai/integrations/grok/stable-audio-3-medium-base-text-to-audio)
- [Grok Build](https://spiral.ai/integrations/grok-build/stable-audio-3-medium-base-text-to-audio)
- [Hermes](https://spiral.ai/integrations/hermes/stable-audio-3-medium-base-text-to-audio)
- [Instinct](https://spiral.ai/integrations/instinct/stable-audio-3-medium-base-text-to-audio)
- [Manus](https://spiral.ai/integrations/manus/stable-audio-3-medium-base-text-to-audio)
- [Muse](https://spiral.ai/integrations/muse/stable-audio-3-medium-base-text-to-audio)
- [Muse Code](https://spiral.ai/integrations/muse-code/stable-audio-3-medium-base-text-to-audio)
- [n8n](https://spiral.ai/integrations/n8n/stable-audio-3-medium-base-text-to-audio)
- [Notion](https://spiral.ai/integrations/notion/stable-audio-3-medium-base-text-to-audio)
- [OpenClaw](https://spiral.ai/integrations/openclaw/stable-audio-3-medium-base-text-to-audio)
- [opencode](https://spiral.ai/integrations/opencode/stable-audio-3-medium-base-text-to-audio)
- [Perplexity](https://spiral.ai/integrations/perplexity/stable-audio-3-medium-base-text-to-audio)
- [Raycast](https://spiral.ai/integrations/raycast/stable-audio-3-medium-base-text-to-audio)
- [VS Code](https://spiral.ai/integrations/vscode/stable-audio-3-medium-base-text-to-audio)
- [Windsurf](https://spiral.ai/integrations/windsurf/stable-audio-3-medium-base-text-to-audio)
- [Zapier](https://spiral.ai/integrations/zapier/stable-audio-3-medium-base-text-to-audio)

## More Codex guides

- [Stable Audio 3 Medium Base Audio to Audio](https://spiral.ai/integrations/codex/stable-audio-3-medium-base-audio-to-audio)
- [Stable Audio 3 Medium Text to Audio](https://spiral.ai/integrations/codex/stable-audio-3-medium-text-to-audio)
- [Stable Audio 3 Medium Base Audio Outpainting](https://spiral.ai/integrations/codex/stable-audio-3-medium-base-audio-outpainting)
- [Stable Audio 3 Small Music Audio to Audio](https://spiral.ai/integrations/codex/stable-audio-3-small-music-audio-to-audio)
- [Stable Audio 3 Medium Base Audio Inpainting](https://spiral.ai/integrations/codex/stable-audio-3-medium-base-audio-inpainting)
- [Stable Audio 3 Small Music Base Audio Inpainting](https://spiral.ai/integrations/codex/stable-audio-3-small-music-base-audio-inpainting)

## Questions about Stable Audio 3 Medium Base Text to Audio in Codex

**Can Codex use Stable Audio 3 Medium Base Text to Audio?**

Yes. Add Spiral to Codex as an MCP server, and Codex can find and run Stable Audio 3 Medium Base Text to Audio like any built-in tool.

**How much does Stable Audio 3 Medium Base Text to Audio cost in Codex?**

$0.06227 per run at the default inputs. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Codex plan is separate.

**Do I need a fal account to use Stable Audio 3 Medium Base Text to Audio in Codex?**

No. Spiral runs Stable Audio 3 Medium Base Text to Audio on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Stable Audio 3 Medium Base Text to Audio in Codex?**

About two minutes: add the hosted server, then sign in.

**Does Codex wait while Stable Audio 3 Medium Base Text to Audio runs?**

Stable Audio 3 Medium Base Text to Audio runs in the background. Codex starts the run, checks on it and gives you the audio when it's ready.

**How long can Stable Audio 3 Medium Base audio be?**

Up to 380 seconds, or 6 minutes and 20 seconds. Use a short clip for a short cue instead of requesting a full-length track.

**Can Stable Audio 3 Medium Base sing lyrics?**

It does not produce intelligible vocals. Vocal-like textures can still appear, so use it for instrumental work rather than songs that require understandable lyrics.

**What does Base mean in Stable Audio 3 Medium Base?**

It identifies the pretrained checkpoint intended for fine-tuning. Stability AI recommends the post-trained Stable Audio 3 Medium for direct generation; use roughly 50 sampling steps when generating with Base.

**What audio quality does Stable Audio 3 Medium Base produce?**

The underlying audio system uses stereo at 44.1 kHz. That describes the audio channels and sample rate, rather than guaranteeing that every generated track will sound finished.

**Which language should I use for descriptions?**

Use English as the documented starting point. The Medium Base model card lists English and does not establish reliable support for other prompt languages.

