Stability Ai Stable Audio 3 Text To Audio

Stability Ai Stable Audio 3 Text To Audio

Playground

Stable Audio 3 Text-to-Audio is a fast AI audio generation model that creates sound effects from text prompts with controllable duration and output format. Ready-to-use REST inference API for sound effect generation, ambient audio, game audio, video production, cinematic sound design, creator content, and professional text-to-audio workflows with simple integration, no coldstarts, and affordable pricing.

Features

Stability AI Stable Audio 3 Text-to-Audio

Stability AI Stable Audio 3 Text-to-Audio generates audio directly from a natural-language prompt, with controls for duration, negative prompting, inference steps, guidance scale, and output format. It is suitable for sound design, ambient scenes, cinematic textures, audio prototyping, and other prompt-driven audio generation workflows.

Why Choose This?

• Prompt-based audio generation
  Generate audio from a text description of mood, environment, texture, or sound event.

• Duration control
  Choose how long the generated audio should be.

• Negative prompt support
  Use negative_prompt to steer the model away from unwanted elements.

• Generation controls
  Adjust num_inference_steps and guidance_scale to balance fidelity, control, and generation behavior.

• Flexible output format
  Export the generated audio in a supported format such as mp3.

• Production-ready API
  Suitable for sound effects, ambience, cinematic scenes, creative prototyping, and audio ideation workflows.

Parameters

How to Use

1. Write your prompt — describe the sound scene, mood, texture, and pacing you want.
2. Set duration (optional) — choose the target audio length.
3. Add a negative prompt (optional) — specify anything you want the model to avoid.
4. Adjust generation settings (optional) — tune num_inference_steps and guidance_scale if needed.
5. Choose output format (optional) — select the format that best fits your workflow.
6. Submit — run the model and download the generated audio.

Example Prompt

30-second cinematic sound-design scene: an isolated desert gas station at midnight with buzzing fluorescent lights, distant highway wind, a loose metal sign creaking, insects around the lamps, and a faraway truck passing slowly. Keep it detailed, spatial, realistic, and non-musical.

Pricing

Just $0.0206 per generation.

Billing Rules

• Each generation costs $0.0206
• Pricing is fixed per request
• duration, negative_prompt, num_inference_steps, guidance_scale, and output_format do not affect pricing

Best Use Cases

• Sound design — Generate cinematic and environmental sound scenes from prompts.
• Ambient audio — Create non-musical background textures and atmosphere beds.
• Creative prototyping — Explore multiple sound directions quickly from text.
• Game and film audio ideation — Produce draft effects and scene ambience for early-stage workflows.
• Content production — Generate custom audio for videos, trailers, podcasts, or installations.

Pro Tips

• Be specific in your prompt about environment, motion, texture, and realism.
• Use negative_prompt when you want to suppress music, vocals, distortion, or unwanted artifacts.
• Increase num_inference_steps if you want potentially more refined output and can tolerate more runtime.
• Adjust guidance_scale when you want tighter prompt adherence.
• Start with a clear, focused prompt before adding extra details.

Notes

• prompt is required.
• Pricing is fixed at $0.0206 per generation.
• Better prompts usually improve both realism and controllability.
• This workflow is especially useful for non-musical and cinematic audio generation.

Related Models

• Other Stability AI audio generation workflows — Useful when you need different quality, speed, or control trade-offs.
• Prompt-based sound generation models — Useful when you want alternate audio styles or generation behavior.

<ApiPage model={model}>
  ## Authentication

  For authentication details, please refer to the [Authentication Guide](/docs-authentication).

  ## API Endpoints

  ### Submit Task & Query Result

  ## Parameters

  ### Task Submission Parameters

  #### Request Parameters

  #### Response Parameters

  <SubmitResponse />

  #### Result Request Parameters

  | Parameter | Type | Required | Default | Description |
  |-----------|------|----------|---------|-------------|
  | id | string | Yes | - | Task ID |

  #### Result Response Parameters

  | Parameter | Type | Description |
  |-----------|------|-------------|
  | code | integer | HTTP status code (e.g., 200 for success) |
  | message | string | Status message (e.g., "success") |
  | data | object | The prediction data object containing all details |
  | data.id | string | Unique identifier for the prediction, the ID of the prediction to get |
  | data.model | string | Model ID used for the prediction |
  | data.outputs | string | Array of generated audio URLs. |
  | data.urls | object | Object containing related API endpoints |
  | data.urls.get | string | URL to retrieve the prediction result |
  | data.status | string | Status of the task: `created`, `processing`, `completed`, or `failed` |
  | data.created_at | string | ISO timestamp of when the request was created (e.g., "2023-04-01T12:34:56.789Z") |
  | data.error | string | Error message (empty if no error occurred) |
  | data.timings | object | Object containing timing details |
  | data.timings.inference | integer | Inference time in milliseconds |

</ApiPage>