Imported from awesome-genmedia/skills (models/stable-audio-2-5-text-to-audio/SKILL.md). Install upstream with npx skills add awesome-genmedia/skills --skill stable-audio-2-5-text-to-audio. Copyright stays with the author.

Stable Audio 2.5 | Text to Audio

Generate audio clips from text descriptions. Create music, sound effects, ambient soundscapes, and more with controllable duration and quality.

Quick Start

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "stable-audio-2-5-text-to-audio",
    "version": "0.0.1",
    "input": {
      "prompt": "A cinematic orchestral score with rising strings and dramatic timpani",
      "seconds_total": 30,
      "guidance_scale": 1,
      "num_inference_steps": 8
    }
  }'

Parameters

Output

• Type: audio

Examples

Sound Effect

{
  "model": "stable-audio-2-5-text-to-audio",
  "version": "0.0.1",
  "input": {
    "prompt": "Thunder rumbling in the distance with heavy rain on a tin roof",
    "seconds_total": 15,
    "guidance_scale": 2,
    "num_inference_steps": 10
  }
}

Background Music

{
  "model": "stable-audio-2-5-text-to-audio",
  "version": "0.0.1",
  "input": {
    "prompt": "Lo-fi hip hop beat with vinyl crackle, mellow piano chords, and a slow drum loop",
    "seconds_total": 60,
    "guidance_scale": 1,
    "num_inference_steps": 8,
    "seed": 77
  }
}

Ambient Soundscape

{
  "model": "stable-audio-2-5-text-to-audio",
  "version": "0.0.1",
  "input": {
    "prompt": "Peaceful forest with birds singing, a gentle stream, and wind through leaves",
    "seconds_total": 120,
    "guidance_scale": 1,
    "num_inference_steps": 8
  }
}

Related Models

• Stable Audio 2.5 Audio to Audio - Transform existing audio clips
• Stable Audio 2.5 Inpaint - Inpaint sections of audio
• Minimax Music V1.5 - Generate music with lyrics

Documentation

• EachLabs API Docs