Audio
Stable Audio 3 Medium Base
Create, transform, repair or extend music and sound with Stable Audio 3 Medium Base.
- Text to audio
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Stable Audio 3 Medium Base. Review your own result before publishing.
A starting point.
Create, transform, repair or extend music and sound with Stable Audio 3 Medium Base.
Before you publish.
Listen to the complete output, including edit boundaries, stereo balance, noise and the ending.
Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.
Settings and model questionsCheck the available settings and guidance when preparing your input.
Inputs and settings
Text mode takes prompt and duration from 1 to 380 seconds. Audio-to-audio also takes an uploaded audio_url and init_noise_level.
Inpainting replaces only mask_start_seconds to mask_end_seconds; the end must follow the start and stay within the uploaded source.
Outpainting needs a positive extend_seconds_before or extend_seconds_after. Raywake checks that the source and extensions fit within 380 seconds.
Choose MP3, WAV, FLAC, OGG, Opus, M4A or AAC. Bitrate applies to compressed formats; base checkpoints expose guidance and more sampling steps.
Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.
Supported inputs
These fields come from the current studio form for stable-audio-3/medium/base/text-to-audio. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | — |
bitrate | Text | Optional | — |
duration | Number | Optional | ≥ 1 · ≤ 380 |
enable_prompt_expansion | On/off | Optional | — |
enable_safety_checker | On/off | Optional | — |
guidance_scale | Number | Optional | ≥ 0 · ≤ 25 |
negative_prompt | Text | Optional | — |
num_inference_steps | Whole number | Optional | ≥ 1 · ≤ 100 |
output_format | Text | Optional | mp3, wav, flac, ogg, opus, m4a, aac |
seed | Whole number | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Other modes and their inputs
Open the operation you need and check its inputs. Settings from one mode do not automatically apply to another.
Audio To Audiostable-audio-3/medium/base/audio-to-audio
Supported inputs
These fields come from the current studio form for stable-audio-3/medium/base/audio-to-audio. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
audio_url | Text | Required | — |
prompt | Text | Required | — |
bitrate | Text | Optional | — |
duration | Number | Optional | ≥ 1 · ≤ 380 |
enable_prompt_expansion | On/off | Optional | — |
enable_safety_checker | On/off | Optional | — |
guidance_scale | Number | Optional | ≥ 0 · ≤ 25 |
init_noise_level | Number | Optional | ≥ 0 · ≤ 1 |
negative_prompt | Text | Optional | — |
num_inference_steps | Whole number | Optional | ≥ 1 · ≤ 100 |
output_format | Text | Optional | mp3, wav, flac, ogg, opus, m4a, aac |
seed | Whole number | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Audio Inpaintingstable-audio-3/medium/base/audio-inpainting
Supported inputs
These fields come from the current studio form for stable-audio-3/medium/base/audio-inpainting. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
audio_url | Text | Required | — |
mask_end_seconds | Number | Required | ≥ 0 · ≤ 380 |
mask_start_seconds | Number | Required | ≥ 0 · ≤ 380 |
prompt | Text | Required | — |
bitrate | Text | Optional | — |
enable_prompt_expansion | On/off | Optional | — |
enable_safety_checker | On/off | Optional | — |
guidance_scale | Number | Optional | ≥ 0 · ≤ 25 |
negative_prompt | Text | Optional | — |
num_inference_steps | Whole number | Optional | ≥ 1 · ≤ 100 |
output_format | Text | Optional | mp3, wav, flac, ogg, opus, m4a, aac |
seed | Whole number | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Audio Outpaintingstable-audio-3/medium/base/audio-outpainting
Supported inputs
These fields come from the current studio form for stable-audio-3/medium/base/audio-outpainting. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
audio_url | Text | Required | — |
prompt | Text | Required | — |
bitrate | Text | Optional | — |
enable_prompt_expansion | On/off | Optional | — |
enable_safety_checker | On/off | Optional | — |
extend_seconds_after | Number | Optional | ≥ 0 · ≤ 380 |
extend_seconds_before | Number | Optional | ≥ 0 · ≤ 380 |
guidance_scale | Number | Optional | ≥ 0 · ≤ 25 |
negative_prompt | Text | Optional | — |
num_inference_steps | Whole number | Optional | ≥ 1 · ≤ 100 |
output_format | Text | Optional | mp3, wav, flac, ogg, opus, m4a, aac |
seed | Whole number | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Stable Audio 3 Medium Base through the API.
Start with this model ID for the endpoint featured on this page:
stable-audio-3/medium/base/text-to-audio
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Available modes
- Text To Audio ·
stable-audio-3/medium/base/text-to-audio - Audio To Audio ·
stable-audio-3/medium/base/audio-to-audio - Audio Inpainting ·
stable-audio-3/medium/base/audio-inpainting - Audio Outpainting ·
stable-audio-3/medium/base/audio-outpainting
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.