# Stable Audio 3 text to audio fal AI small music base

Needs prompt.

Stable Audio 3, served by fal.ai. $0.0281 per audios One submitted item is offered per call; the exact receipt determines the final charge. Asynchronous: returns a request_id; poll fal/status and fetch fal/result with model "fal-ai/stable-audio-3" and that request_id. The exact endpoint/request billing receipt is required before settlement.

- Tool ID: `fal/fal-ai-stable-audio-3-small-music-base-text-to-audio`
- Name in the catalog: Stable Audio 3, text to audio
- Provider: [fal.ai](/providers/fal.md)
- Capability: [AI audio](/tools/audio-generation.md)
- Price: $0.0281 per call
- Authentication: an authorised Agentik workspace is required for execution, including zero-price tools.

## Pricing contract

The provider’s price, with no markup. Billed for measured usage.


```json
{
  "model": "per_call",
  "amountUsd": 0.0281
}
```

Pricing source: [https://fal.ai/models/fal-ai/stable-audio-3/small/music/base/text-to-audio/llms.txt](https://fal.ai/models/fal-ai/stable-audio-3/small/music/base/text-to-audio/llms.txt). $0.0281 per audios One submitted item is offered per call; the exact receipt determines the final charge..

Price verification date: 2026-11-03.

## Complete input schema


```json
{
  "type": "object",
  "properties": {
    "prompt": {
      "title": "Prompt",
      "description": "Text description of the audio to generate.",
      "type": "string"
    },
    "duration": {
      "title": "Duration",
      "default": 30,
      "minimum": 1,
      "description": "Duration of the generated audio in seconds.",
      "type": "number",
      "maximum": 120
    },
    "seed": {
      "title": "Seed",
      "description": "Random seed for reproducible outputs. Omit for a random seed.",
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ]
    },
    "guidance_scale": {
      "title": "Guidance Scale",
      "default": 7,
      "minimum": 0,
      "description": "Classifier-free guidance scale. Higher values follow the prompt more strictly; ~7.0 is a good starting point for base checkpoints.",
      "type": "number",
      "maximum": 25
    },
    "num_inference_steps": {
      "title": "Num Inference Steps",
      "default": 50,
      "minimum": 1,
      "description": "Number of sampling steps. Base (non-distilled) checkpoints typically need ~50 for good quality.",
      "type": "integer",
      "maximum": 100,
      "enum": [
        50
      ]
    },
    "bitrate": {
      "title": "Bitrate",
      "default": "192k",
      "description": "Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).",
      "type": "string"
    },
    "output_format": {
      "title": "Output Format",
      "default": "mp3",
      "description": "Container format for the generated audio output.",
      "type": "string",
      "enum": [
        "mp3",
        "wav",
        "flac",
        "ogg",
        "opus",
        "m4a",
        "aac"
      ]
    },
    "negative_prompt": {
      "title": "Negative Prompt",
      "default": "",
      "description": "Text description of qualities to avoid in the output.",
      "type": "string"
    },
    "enable_prompt_expansion": {
      "title": "Enable Prompt Expansion",
      "default": false,
      "description": "If True, the prompt will be expanded using an LLM for more detailed and higher quality results.",
      "type": "boolean",
      "enum": [
        false
      ]
    },
    "enable_safety_checker": {
      "title": "Enable Safety Checker",
      "default": true,
      "description": "Enable NSFW content safety checking.",
      "type": "boolean"
    }
  },
  "required": [
    "prompt"
  ],
  "additionalProperties": false
}
```

## Published example

This is the provider tool’s published example. Replace example values with the user’s requested inputs, respecting the schema; do not execute an example merely to test a connection.


```json
{
  "tool_id": "fal/fal-ai-stable-audio-3-small-music-base-text-to-audio",
  "input": {
    "prompt": "An anthemic Pop Rock instrumental that fills your head with nostalgic thoughtfulness",
    "enable_prompt_expansion": false,
    "num_inference_steps": 50,
    "duration": 30,
    "guidance_scale": 7,
    "bitrate": "192k",
    "output_format": "mp3",
    "negative_prompt": "",
    "enable_safety_checker": true
  }
}
```

## Execute and retrieve

Inspect again before execution, explain the price and obtain the required authority. Use MCP run_tool or POST /v1/run with this tool ID, valid input and an idempotency key. Save the returned run ID and follow the actual state. If Agentik answers that the tool is temporarily unavailable, do not retry it blindly; use discovery to propose an alternative.

This tool uses deferred settlement. Follow its returned task/run instructions; preserve the existing reservation until the result is reconciled.

A partial or uncertain result can still have consumed provider resources. Consult [billing](/docs/billing.md), [idempotency](/docs/idempotency.md) and [asynchronous results](/docs/async.md).

[Provider documentation](https://fal.ai/models/fal-ai/stable-audio-3/small/music/base/text-to-audio)

[REST inspection](https://api.agentik.cc/v1/tools/fal/fal-ai-stable-audio-3-small-music-base-text-to-audio) · [OpenAPI](/openapi.json) · [Connection guide](/connect.md)

---

[HTML page](/providers/fal/fal-ai-stable-audio-3-small-music-base-text-to-audio) · [Agent index](/llms.txt)