Stable Audio 3 Medium Save up to 27%stable-audio-3-medium
Type
Spec
Rate
Generation
per request
$0.0479$0.035
Stable Audio 3 Medium and Stable Audio 2.5 side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
Stability AI Audio GenerationStable Audio 3 Medium and Stable Audio 2.5 are both Stability AI models in the Audio Generation category, available through the EmpirioLabs API.
| Spec | Stable Audio 3 Medium | Stable Audio 2.5 |
|---|---|---|
| Model ID | stable-audio-3-medium | stable-audio-2-5 |
| Author | Stability AI | Stability AI |
| Released | May 20, 2026 | Sep 10, 2025 |
| Input | Text | Text |
| Output | Audio | Audio |
| Endpoints | POST /v1/audio/generations | POST /v1/audio/generations |
| Capabilities |
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | Stable Audio 3 Medium | Stable Audio 2.5 |
|---|---|---|
| prompt | string | string |
| audio_duration | 1 to 380 Default: 30 | - |
| num_inference_steps | 4 to 8 Default: 8 | - |
| seed | 0 to 2147483647 | number |
| format | mp3, wav, flac, ogg Default: mp3 | - |
| response_format | url, b64_json Default: url | - |
| return_base64 | boolean Default: false | - |
| mode | - | text-to-audio, audio-to-audio, audio-inpaint Default: text-to-audio |
| output_format | - | mp3, wav Default: mp3 |
| duration | - | 1 to 190 Default: 190 |
| steps | - | 4 to 8 Default: 8 |
| cfg_scale | - | 1 to 25 Default: 1 |
| strength | - | 0.01 to 1 Default: 1 |
| mask_start | - | 0 to 190 Default: 30 |
| mask_end | - | 0 to 190 Default: 190 |
| random_seed | - | boolean Default: true |
Generates music and sound effects from text: 44.1 kHz stereo, from 1 to 380 seconds per clip. Powered by Stability AI.
Adds audio-inpaint mode (regenerate a time window) on top of Stable Audio 2.0.
Stable Audio 3 Medium runs through POST /v1/audio/generations. The request returns a job_id right away; poll GET /v1/jobs/{job_id} until the job completes and read the output URLs from the result. Both models are called through the same endpoint. Set model to stable-audio-3-medium or stable-audio-2-5. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/audio/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "stable-audio-3-medium",
"prompt": "Describe what you want Stable Audio 3 Medium to generate."
}'Prompt tests and comparison runs that cover both models.
Stable Audio 3 Medium is the newer release (May 20, 2026); Stable Audio 2.5 was released on Sep 10, 2025. Capabilities listed only for Stable Audio 3 Medium: seed control. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
Stable Audio 3 Medium is the newer release (May 20, 2026); Stable Audio 2.5 was released on Sep 10, 2025.
The two models are priced on different units or tiers, so compare the live rate cards on this page. They always match what the API charges.
Yes. Both models use POST /v1/audio/generations with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.
