self-hosted/ai
§01·recipe · tts

Foundation-1 on RTX 5060 Ti: Structured Music Sample Generation

ttsintermediate8GB+ VRAMMay 19, 2026
models
tools
tested on
→ all recipes tested on RTX 5060 Ti
prerequisites
  • NVIDIA RTX 5060 Ti (16 GB VRAM) or any GPU with ≥ 8 GB VRAM
  • Python 3.10 (3.11+ may fail dependency resolution per the RC fork README)
  • Git, ~3 GB free disk for weights + dependencies

What You'll Build

A local, offline pipeline that turns structured tag prompts (instrument → timbre → FX → key → bars → BPM) into tempo-synced, bar-aligned music loops on your RTX 5060 Ti. Foundation-1 is a fine-tune of stabilityai/stable-audio-open-1.0 trained for music-production workflows; the RC Stable Audio Tools fork handles the BPM/bar timing alignment automatically.

Hardware data: RTX 5060 Ti (16 GB VRAM) · ~7 GB VRAM during generation per the HuggingFace model card · See benchmark data

ℹ️ Not a text-to-speech model. Foundation-1 is in our tts vertical because the catalogue groups all audio models together, but it generates one-shot music samples — bar-locked instrumental loops — not speech. It does not synthesize voices, words, or any spoken audio. For speech synthesis on this GPU, see Kokoro, VoxCPM, or Qwen3-TTS instead. Per its own HuggingFace card: "specialized model for music sample generation, not a general-purpose music generator."

⚠️ Licensing — read before shipping. Foundation-1 weights are released under the Stability AI Community License. The HuggingFace card states the model "is available for non-commercial use or limited commercial use by entities with annual revenues below USD $1M. For revenues exceeding USD $1M, please refer to the repository license file for full terms." If you're a hobbyist or under the $1M threshold you're clear; otherwise contact Stability AI for a commercial license before publishing or selling outputs. (The RC fork code is MIT; the constraint is on the model weights.)

Requirements

ComponentMinimumTested
GPU8 GB VRAM (per HF card)RTX 5060 Ti (16 GB)
RAM16 GB system RAM—
Storage~3 GB (2.43 GB weights + venv + deps)—
Python3.10 (3.11+ may fail SciPy resolution)—
PyTorch2.7+ with CUDA 12.8 wheel for Blackwell (sm_120)—
SoftwareRC Stable Audio Tools fork or ComfyUI custom node—

Installation

This recipe follows the canonical workflow recommended on the Foundation-1 model card — the RC Stable Audio Tools fork, which auto-handles BPM/bar timing alignment. For a ComfyUI alternative, see Troubleshooting.

1. Clone the RC Stable Audio Tools fork

git clone https://github.com/RoyalCities/RC-stable-audio-tools.git
cd RC-stable-audio-tools

2. Create a Python 3.10 virtual environment

Linux / macOS:

python3.10 -m venv venv
source venv/bin/activate

Windows:

py -3.10 -m venv venv
venv\Scripts\activate

3. Install stable-audio-tools and the fork

pip install stable-audio-tools
pip install .

4. Replace torch with the Blackwell-compatible wheel

The RC fork's Windows install line pins CUDA 12.1 (whl/cu121) — that wheel does not ship sm_120 kernels and will fail on RTX 5060 Ti with a no kernel image is available for execution error. Reinstall torch from the CUDA 12.8 channel (PyTorch Blackwell guidance):

pip uninstall -y torch torchvision torchaudio
pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu128

(Once stable PyTorch 2.7+ with cu128 lands in the default index, drop the --pre flag and the nightly URL.)

5. Download Foundation-1 weights

Place both files inside a single subfolder of models/:

mkdir -p models/Foundation-1
cd models/Foundation-1
curl -L -o Foundation_1.safetensors \
  https://huggingface.co/RoyalCities/Foundation-1/resolve/main/Foundation_1.safetensors
curl -L -o model_config.json \
  https://huggingface.co/RoyalCities/Foundation-1/resolve/main/model_config.json
cd ../..

The safetensors file is 2.43 GB (HF Files tab).

Running

Launch the Gradio UI, pointing at the Foundation-1 checkpoint and config you just downloaded:

python run_gradio.py \
  --model-config models/Foundation-1/model_config.json \
  --ckpt-path models/Foundation-1/Foundation_1.safetensors

The Gradio interface opens in your browser. Foundation-1 uses a layered tag prompt schema documented on its model card:

[Instrument Family / Sub-Family], [Timbre], [Musical Behavior / Notation], [FX], [Key], [Bars], [BPM]

A working example prompt from the card:

Bass, FM Bass, Medium Delay, Medium Reverb, Low Distortion, Phaser, Sub Bass,
Bass, Upper Mids, Acid, Gritty, Wide, Dubstep, Thick, Silky, Warm, Rich,
Overdriven, Crisp, Deep, Clean, Pitch Bend, 303, 8 Bars, 140 BPM, E minor

Supported loop structures: 4 or 8 bars; supported BPMs: 100, 110, 120, 128, 130, 140, 150. The RC fork's BPM/bar selector locks generation duration to the prompt's musical structure automatically — for an 8-bar loop at 100 BPM that's roughly 19 seconds of output (model card). The underlying Stable Audio Open base outputs 44.1 kHz stereo up to 47 seconds; Foundation-1 is constrained to the bar/BPM grid above.

Results

  • Speed: The model card reports generation takes "approximately ~7–8 seconds per sample" on an RTX 3090. No comparable-GPU number has been published for the RTX 5060 Ti yet; check /check/foundation-1/rtx-5060-ti for live benchmark data as it lands.
  • VRAM usage: ~7 GB during generation per the HF card ("Typical VRAM usage during generation is approximately ~7 GB. For reliable operation, a GPU with at least 8 GB of VRAM is recommended"). The 5060 Ti's 16 GB headroom leaves room for parallel jobs or running alongside a DAW.
  • Output: mono/stereo .wav loops aligned to the requested bar count and BPM. Per the model card limitations, percussion and drum sounds are out of scope for this release; the 10 instrument families covered are Synth, Keys, Bass, Bowed Strings, Mallet, Wind, Guitar, Brass, Vocal, and Plucked Strings.

For the full benchmark data, see /check/foundation-1/rtx-5060-ti.

Troubleshooting

RuntimeError: CUDA error: no kernel image is available for execution on the device

You installed the default pip install torch wheel (or the RC README's whl/cu121 line) — neither ships sm_120 kernels for Blackwell. Reinstall from whl/nightly/cu128 per step 4 above. Tracking: PyTorch Blackwell guidance.

Dependency resolution failures on Python 3.11+

The RC fork's README explicitly notes 3.11+ "can fail dependency resolution due to pinned SciPy wheels." Use a Python 3.10 venv as in step 2.

Prefer ComfyUI over Gradio

Two community ComfyUI custom nodes exist:

  • Saganaki22/ComfyUI-Foundation-1 — auto-downloads weights into ComfyUI/models/stable_audio/Foundation-1/, ships example workflows. Installs via git clone into ComfyUI/custom_nodes/ then python install.py (which installs stable-audio-tools --no-deps to protect your ComfyUI environment from the upstream's aggressive pandas==2.0.2 / numpy==1.23 pins).
  • SanDiegoDude/scg_Foundation-1-comfyUI — install via ComfyUI Manager recommended; weights land at ComfyUI/models/audio_checkpoints/Foundation-1/.

Same ~7 GB VRAM and 8 GB minimum apply regardless of front-end.

Prompt produces drift or incoherent phrases

Per the model card's Limitations section, if generation duration doesn't match the prompt's bar/BPM structure (e.g. requesting an 8-bar loop but capping output at 5 seconds), output coherence degrades. The RC fork handles this alignment automatically — if you're using bare stable-audio-tools or a third-party UI, set the audio duration manually to match the bars × (60 / BPM) × 4 formula. Also: keep prompts in the documented tag order, use 1–3 timbre descriptors, and always include both Bars and BPM.

Percussion or drum prompts produce garbage

By design. The card lists percussion as explicitly out-of-scope for this release. Use a different tool (e.g. a drum sample library or a percussion-specific model) for drum loops.

No widely-reported issues on RTX 5060 Ti specifically — if you hit one, report it via the submission form.