stable-audio-2.5

Prerequisites

Install and load these skills before generating (skip if already in context via @pruna):

Or install the full suite once: npx skills add PrunaAI/pruna-skills@pruna -y

Follow each skill's Before generating / craft sections — do not restate guide content here.

Agent habit

In the first reply, name `stable-audio-2.5` in backticks, confirm REPLICATE_API_TOKEN (or stop with signup links from pruna-api), then ask for required inputs. Open intake → generation-diversity clarification intake before the first POST. Redirect when When NOT to use fits better.

When NOT to use

Use a different skill instead:

Environment

export REPLICATE_API_TOKEN=r8_...

Requires ffmpeg and ffprobe on PATH for the mix step.

HTTP (curl)

curl -s -X POST \
  -H "Authorization: Bearer ${REPLICATE_API_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "input": {
      "prompt": "Instrumental light electronic pop bed, soft groove and mellow synth pads, calm positive tech atmosphere, understated background music, no vocals, 94 BPM",
      "duration": 90,
      "steps": 8,
      "cfg_scale": 1
    }
  }' \
  "https://api.replicate.com/v1/models/stability-ai/stable-audio-2.5/predictions"

Poll urls.get until status is succeeded; download output MP3.

Before generating

1. Complete Prerequisites guide reading order — bed prompt craft: audio-prompting Worked examples (instrumental bed).
2. Confirm prompt, duration (match or slightly exceed reel length), and mix volume (~0.08–0.15 under VO). When listing fields, name REPLICATE_API_TOKEN (Replicate — not PRUNA_API_KEY).
3. Model notes: lead with Instrumental and no vocals. Duration 1–190s. Prefer understated beds (BPM ~88–98 for tech launch reels) so music does not compete with dialogue.

Required input

• prompt (string)

Common optional fields

• duration — seconds, 1–190
• steps — 4–8 (default 8)
• cfg_scale — 1–25 (default 1)
• seed — optional integer

Typical next steps

Common follow-ons after this skill: