Stable Audio 3 Medium · Text to Audio
fal-ai/stable-audio-3/medium/text-to-audioTurn text into speech and audio with Stable Audio 3 Medium · Text to Audio from fal through one Spiral API key. It runs in the background and returns audio. Pay as you go, with no subscription.
Pricing
$0.04888 per run at the default inputs.
Limits
- Runs
- In the background
- Returns
- audio
- Longest queue wait
- 1 hour
- Run deadline
- 30 minutes
- Longest run, end to end
- 255 minutes
- Largest inline input
- 1 MB
- Largest input file
- 2 GB
- Largest output
- 5 GB
Input
| Field | Kind | Default | Description |
|---|---|---|---|
negative_prompt | text | Text description of qualities to avoid in the output. | |
duration | number 1 to 380 | 30 | Duration of the generated audio in seconds. The medium model supports up to 380 seconds (~6m20s). |
num_inference_steps | number (whole) 1 to 100 | 8 | Number of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher. |
guidance_scale | number 0 to 25 | 1 | Classifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints. |
seed | number (whole) | — | Random seed for reproducible outputs. Omit for a random seed. |
enable_prompt_expansion | true or false | false | If True, the prompt will be expanded using an LLM for more detailed and higher quality results. |
output_format | one of mp3, wav, flac, ogg, opus, m4a, aac | mp3 | Container format for the generated audio output. |
bitrate | text | 192k | Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac). |
prompt required | text | — | Text description of the audio to generate. |
Same request in code
curl https://api.spiral.ai/v1/runs \
-H "Authorization: Bearer $SPIRAL_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"provider": "fal",
"model": "fal-ai/stable-audio-3/medium/text-to-audio",
"input": {
"prompt": "An anthemic Pop Rock instrumental that fills your head with nostalgic thoughtfulness"
}
}'Frequently asked questions
How much does Stable Audio 3 Medium · Text to Audio cost?
$0.04888 per run at the default inputs. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.
How do I use Stable Audio 3 Medium · Text to Audio through an API?
Send `POST /v1/runs` with `"provider": "fal"`, `"model": "fal-ai/stable-audio-3/medium/text-to-audio"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.
Do I need an account with fal to use Stable Audio 3 Medium · Text to Audio?
No. Spiral runs it on its own fal account and charges your Spiral balance.
Can my AI agent use Stable Audio 3 Medium · Text to Audio?
Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.