GET
/v1/schemas/fal/audio/fal-ai%2Fstable-audio-3%2Fmedium%2Ftext-to-audio
Accept:
Request body
11 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| prompt* | string | Text description of the audio to generate. | |
| bitrate | string | Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac). | default: "192k" |
| seed | integer | Random seed for reproducible outputs. Omit for a random seed. | nullable |
| guidance_scale | number | Classifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints. | 0 ≤ n ≤ 25 · default: 1 |
| enable_prompt_expansion | boolean | If True, the prompt will be expanded using an LLM for more detailed and higher quality results. | default: false |
| num_inference_steps | integer | Number of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher. | 1 ≤ n ≤ 100 · default: 8 |
| output_format | enum | Container format for the generated audio output. | mp3 | wav | flac | ogg | opus | m4a · +1 more · default: "mp3" |
| duration | number | Duration of the generated audio in seconds. The medium model supports up to 380 seconds (~6m20s). | 1 ≤ n ≤ 380 · default: 30 |
| sync_mode | boolean | If True, the audio is returned inline as a data URI and the result is not saved to the request history. | default: false |
| enable_safety_checker | boolean | Enable NSFW content safety checking. | default: true |
| negative_prompt | string | Text description of qualities to avoid in the output. | default: "" |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/stable-audio-3/medium/text-to-audio","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}