How to Use Stable Audio 3 Medium Base Audio Outpainting in opencode
Extend existing music or sound recordings with a text-guided continuation. Unlike Stable Audio 3 Medium, Stable Audio 3 Medium Base Audio Outpainting uses the pre-trained checkpoint, which needs about 50 sampling steps.
Prompts to try with Stable Audio 3 Medium Base Audio Outpainting in opencode
Copy an example into opencode, or ask in your own words.
Use Stable Audio 3 Medium Base Audio Outpainting to extend assets/audio/menu.wav from 30 to 50 seconds. Describe soft electric piano and restrained brushed drums with a calm mood, and save a preview for the menu scene.
Use Stable Audio 3 Medium Base Audio Outpainting to add 15 seconds after the 45-second instrumental in assets/audio/demo.wav. Request gentle synth chords and sparse percussion, using 50 sampling steps and guidance 7.
Use Stable Audio 3 Medium Base Audio Outpainting to extend assets/audio/forest.wav from 20 to 50 seconds. Request quiet wind, distant birds, and a steady woodland atmosphere; make the result available for playback in the scene.
Use Stable Audio 3 Medium Base Audio Outpainting to add a 10-second continuation to assets/audio/engine-drone.wav, which is 12 seconds long. Describe a low mechanical rumble that gradually softens.
Use Stable Audio 3 Medium Base Audio Outpainting to create two 15-second endings for the 40-second cue in assets/audio/outro.wav. Request solo piano for one and piano with soft strings for the other, then build a preview that lets me compare them.
How to set up Stable Audio 3 Medium Base Audio Outpainting in opencode
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Leave out --global to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
- Sign in
Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, /mcps starts the same sign-in.
opencode mcp auth spiral
- Check it
Spiral shows as connected.
opencode mcp list
Use the Spiral skill
- Send opencode this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Stable Audio 3 Medium Base Audio Outpainting
One request; the result comes back by polling or a webhook.
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/audio-outpainting", "input": { "prompt": "soft strings continue the melody", "audio_url": "https://storage.googleapis.com/falserverless/model_tests/diffrythm/rock_en.wav" } }'
Then paste one of the prompts above: opencode finds Stable Audio 3 Medium Base Audio Outpainting on Spiral, shows the price and runs it.
Stable Audio 3 Medium Base Audio Outpainting providers and prices
Spiral runs Stable Audio 3 Medium Base Audio Outpainting through fal. Open a card for today's price, with every fee included.
$0.07202 per run at the default inputs.
Settings you can ask for
Stable Audio 3 Medium Base Audio Outpainting works from your prompt and audio URL. Ask opencode for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Negative prompt | what to leave out, in words | Text description of qualities to avoid in the output. | |
| Number of 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 | a whole number | Random seed for reproducible outputs. Omit for a random seed. | |
| Enable prompt expansion | on or off | off | If True, the prompt will be expanded using an LLM for more detailed and higher quality results. |
| Output format | mp3, wav, flac, ogg, opus, m4a, or aac | mp3 | Container format for the generated audio output. |
| Extend seconds before | 0 to 380 | 0 | Seconds of new audio to generate before the source audio. |
| Extend seconds after | 0 to 380 | 0 | Seconds of new audio to generate after the source audio. |
Every API field of Stable Audio 3 Medium Base Audio Outpainting · Audio Outpainting Medium Base is on its tool page: open its card above.
What can you do with Stable Audio 3 Medium Base Audio Outpainting in opencode?
Extend project music and sound assets to fit longer scenes, demos, or gameplay sequences. Use the existing recording and an English description to request each continuation, then review the result in context.
Longer podcast music beds
Extend an existing instrumental bed to cover a longer introduction or transition. Describe a sparse arrangement that leaves room for the host.
Background music for product demos
Continue an existing music cue when a screen recording runs longer than planned. Request the same instruments and mood for the added section.
Game scene ambience
Extend a short environmental recording into a longer background bed for a game scene. Describe the sound source and atmosphere to guide the continuation.
Instrumental phrase development
Continue a recorded musical idea with another phrase. Try descriptions of the lead instrument, accompaniment, and desired energy.
Longer sound effect tails
Extend a recorded drone, rumble, or sustained effect for a longer shot. Describe how the sound should develop through the added section.
Alternative music endings
Explore different continuations of the same instrumental recording, such as a restrained piano ending or a fuller percussion section. Compare the results before choosing an edit.
More on Stable Audio 3 Medium Base Audio Outpainting and opencode
Overview
Stable Audio 3 Medium Base Audio Outpainting in other agents
Questions about Stable Audio 3 Medium Base Audio Outpainting in opencode
Can opencode use Stable Audio 3 Medium Base Audio Outpainting?
Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Stable Audio 3 Medium Base Audio Outpainting like any built-in tool.
How much does Stable Audio 3 Medium Base Audio Outpainting cost in opencode?
$0.07202 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 opencode plan is separate.
Do I need a fal account to use Stable Audio 3 Medium Base Audio Outpainting in opencode?
No. Spiral runs Stable Audio 3 Medium Base Audio Outpainting 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 Audio Outpainting in opencode?
About two minutes: add the server, then sign in, then check it.
Does opencode wait while Stable Audio 3 Medium Base Audio Outpainting runs?
Stable Audio 3 Medium Base Audio Outpainting runs in the background. opencode starts the run, checks on it and gives you the audio when it's ready.
What is Stable Audio 3 Medium Base Audio Outpainting useful for?
It extends an existing stereo recording with new audio guided by a description. Suggested uses include longer instrumental beds, additional musical phrases, and extended soundscapes.
How is Medium Base different from Stable Audio 3 Medium?
Medium Base is the pre-trained checkpoint that Stability AI positions for fine-tuning. Its inference guidance calls for about 50 sampling steps, while the post-trained checkpoint uses eight.
How long can the audio be?
Stability AI documents a Medium track limit of 6 minutes 20 seconds, or 380 seconds. Plan the source recording and its extension within that total.
Can it generate narration or dialogue?
Stable Audio 3 is not designed for speech or voice generation. Use it for music and sound continuation rather than spoken scripts.
Which language should I use for descriptions?
Use English. Stability AI says the models were trained on English descriptions and that other languages underperform.
Start using Stable Audio 3 Medium Base Audio Outpainting in opencode
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into opencode:
set up https://spiral.ai/SKILL.md


