fal-ai/stable-audio-3-trainer

Stable Audio 3 LoRA Trainer fine-tunes Stable Audio 3 base models on paired audio-caption datasets, producing compact LoRA weights that adapt generation toward a custom music style, sound palette, or domain.

Training

Commercial use

Schema

LLMs

Playground API

Input

Audio Data Url*

Hint: Drag and drop files from your computer, images from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL.

Additional Settings

Customize your input with more control.

Your request will cost $3.00 per 1000-step training run. It scales per step, so a 2000-step training run will cost $6.00. Training with batch_size > 1 bills additional units proportional to batch_size × clip duration.

Training history

See all

Nothing here yet...

Fine-tune your training parameters and start right now.

Note: these are the most recent training requests. For the full history, check the requests tab.

Stable Audio 3 LoRA Trainer

Fine-tune a Stable Audio 3 base model into a LoRA that adapts it to your own style, instrument, or sound. The output is a small .safetensors file you load on the Stable Audio 3 inference endpoints (the /lora variants).

Dataset

Provide a .zip archive (via audio_data_url) of audio clips, each paired with a .txt caption that has the same basename:


my_dataset.zip
├── clip1.wav
├── clip1.txt        # text prompt describing clip1
├── clip2.flac
├── clip2.txt
└── ...

Audio: WAV, FLAC, MP3, OGG, OPUS, or AIFF (WAV/FLAC recommended). 4–2000 clips.
Captions: one non-empty UTF-8 .txt per clip. Describe the audio the way you would prompt the model — e.g. genre, instruments, mood, and BPM for music; source, action, and recording character for SFX.
Mixed clip lengths are fine; clips longer than the model's max are cropped.

Models (`model`)

Model	Use for	Max clip length
`medium-base` (default)	music, stems, SFX	~6 min (380 s)
`small-music-base`	music, stems	2 min
`small-sfx-base`	sound effects	2 min

Key parameters

Parameter	Default	Notes
`number_of_steps`	1000	1–20000. ~500–2000 is typical; more = stronger adaptation.
`rank`	16	1–256. Higher = more expressive and a larger file. `-xs` adapters require ≤ 17.
`learning_rate`	1e-4	AdamW learning rate for the LoRA.
`adapter_type`	`dora-rows`	One of `lora`, `dora`, `dora-rows`, `dora-cols`, `bora`, or their `-xs` variants (minimal parameters/VRAM).
`duration`	auto	Crop length in seconds. Auto-detected from the longest clip and capped at the model's max.
`batch_size`	1	1–8, must be ≤ the number of clips. Values > 1 bill extra units proportional to batch size × clip duration.
`base_precision`	`bf16`	Precision of the frozen base weights (LoRA stays fp32).
`seed`	42	For reproducible runs.

Advanced: include / exclude (limit which layers receive LoRA), lora_checkpoint_url (resume from an existing .safetensors), and pre_encode (pre-encode audio to latents before training).

Output

lora_file — the trained .safetensors LoRA.
config_file — JSON metadata for the run (model, steps, rank, etc.).

Load lora_file on the matching Stable Audio 3 inference endpoint's /lora variant (e.g. /medium/text-to-audio/lora) to generate with your fine-tune.

Stable Audio 3 LoRA Trainer

Dataset

Provide a .zip archive (via audio_data_url) of audio clips, each paired with a .txt caption that has the same basename:


my_dataset.zip
├── clip1.wav
├── clip1.txt        # text prompt describing clip1
├── clip2.flac
├── clip2.txt
└── ...

Audio: WAV, FLAC, MP3, OGG, OPUS, or AIFF (WAV/FLAC recommended). 4–2000 clips.
Captions: one non-empty UTF-8 .txt per clip. Describe the audio the way you would prompt the model — e.g. genre, instruments, mood, and BPM for music; source, action, and recording character for SFX.
Mixed clip lengths are fine; clips longer than the model's max are cropped.

Models (`model`)

Model	Use for	Max clip length
`medium-base` (default)	music, stems, SFX	~6 min (380 s)
`small-music-base`	music, stems	2 min
`small-sfx-base`	sound effects	2 min

Key parameters

Parameter	Default	Notes
`number_of_steps`	1000	1–20000. ~500–2000 is typical; more = stronger adaptation.
`rank`	16	1–256. Higher = more expressive and a larger file. `-xs` adapters require ≤ 17.
`learning_rate`	1e-4	AdamW learning rate for the LoRA.
`adapter_type`	`dora-rows`	One of `lora`, `dora`, `dora-rows`, `dora-cols`, `bora`, or their `-xs` variants (minimal parameters/VRAM).
`duration`	auto	Crop length in seconds. Auto-detected from the longest clip and capped at the model's max.
`batch_size`	1	1–8, must be ≤ the number of clips. Values > 1 bill extra units proportional to batch size × clip duration.
`base_precision`	`bf16`	Precision of the frozen base weights (LoRA stays fp32).
`seed`	42	For reproducible runs.

Advanced: include / exclude (limit which layers receive LoRA), lora_checkpoint_url (resume from an existing .safetensors), and pre_encode (pre-encode audio to latents before training).

Output

lora_file — the trained .safetensors LoRA.
config_file — JSON metadata for the run (model, steps, rank, etc.).

Load lora_file on the matching Stable Audio 3 inference endpoint's /lora variant (e.g. /medium/text-to-audio/lora) to generate with your fine-tune.

fal-ai/stable-audio-3-trainer

Input

Training history

Nothing here yet...

Stable Audio 3 LoRA Trainer

Dataset

Models (model)

Key parameters

Output

Stable Audio 3 LoRA Trainer

Dataset

Models (model)

Key parameters

Output

Models (`model`)

Models (`model`)