Type
Spec
Rate
Generation
per 10,000 characters
$0.14
StepAudio 3 Gen and StepAudio 3 Music side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
StepFun Audio GenerationStepAudio 3 Gen and StepAudio 3 Music are both StepFun models in the Audio Generation category, available through the EmpirioLabs API.
| Spec | StepAudio 3 Gen | StepAudio 3 Music |
|---|---|---|
| Model ID | stepaudio-3-gen | stepaudio-3-music |
| Author | StepFun | StepFun |
| Released | Sep 9, 2026 | Sep 8, 2026 |
| Input | Text | Text Audio |
| Output | Audio | Audio |
| Region | International | International |
| 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 | StepAudio 3 Gen | StepAudio 3 Music |
|---|---|---|
| prompt | string | string |
| instruction | max 500 | - |
| roles | string | - |
| scripts | string | - |
| response_format | mp3, wav, flac, opus, pcm Default: mp3 | mp3, wav, flac, opus, pcm Default: mp3 |
| sample_rate | 8000, 16000, 22050, 24000, 48000 Default: 24000 | - |
| speed | 0.5 to 2 Default: 1 | - |
| volume | 0.1 to 2 Default: 1 | - |
| text_normalization | standard, enhanced Default: standard | - |
| lyrics | - | string |
| task | - | text_to_music, music_cover, vocal_to_music Default: text_to_music |
| instrumental | - | boolean Default: false |
| song_audio | - | string |
| vocal_audio | - | string |
| temperature | - | 0.01 to 2 Default: 0.85 |
| top_p | - | 0 to 1 Default: 0.92 |
One finished clip with spoken lines, sound effects, ambience, and background music together. Text in prompt and scripts is spoken as written: describe the setting and background music in instruction, wrap a sound effect or music cue in square brackets, and put a delivery direction in parentheses. Send a prompt, or use roles and scripts for multi-speaker control. Roles and instruction are capped at 500 characters each and scripts at 1,000. Output formats are mp3, wav, flac, opus, and pcm. Reference voices and voice cloning are not available on this model. This model is in preview and its capabilities may change.
Describe the style and the model writes and performs a complete song. Supply lyrics or let the model write them, set instrumental for a track with no vocals, or attach a reference song for a cover or a dry vocal to build an arrangement around. Section tags such as [Verse], [Chorus], and [Outro] shape the structure. Output length is chosen by the model and is typically one to three minutes, so it is not set by a parameter and two runs of the same prompt can differ. Billing follows the generated length. Instrumental and lyrics cannot be combined. This model is in preview and its capabilities may change.
StepAudio 3 Gen 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 stepaudio-3-gen or stepaudio-3-music. 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": "stepaudio-3-gen",
"prompt": "Describe what you want StepAudio 3 Gen to generate."
}'StepAudio 3 Gen is the newer release (Sep 9, 2026); StepAudio 3 Music was released on Sep 8, 2026. Input types only StepAudio 3 Music accepts: Audio. Capabilities listed only for StepAudio 3 Gen: text to speech, sound effects, voice control. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
StepAudio 3 Gen is the newer release (Sep 9, 2026); StepAudio 3 Music was released on Sep 8, 2026.
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.