# Audio Studio MCP

> Local Stable Audio 3 for temp score and SFX: generate, inpaint, extend, loop and loudness-normalize offline.

- **Category:** Sound Design & SFX
- **Vendor:** Community (KanaWorks_AI / kanaworksai-hue) (community)
- **Pricing:** free
- **Verified:** 2026-10-23

## What it does

Community MCP server that runs Stability AI's open Stable Audio 3 weights on your own machine — MLX on Apple Silicon, PyTorch on NVIDIA — to generate instrumental music beds, stems and sound effects from text, 1–4 seeded candidates per call. It goes past generation: edit_audio re-styles a clip, regenerates a time range or extends a track, and process_audio trims, loops, fades and normalizes to a LUFS target before writing WAV, OGG or FLAC with a JSON sidecar recording prompt and seed. For a filmmaker-agent that is a free, reproducible temp-score and foley-draft loop that never uploads the cut.

## Connect

- Claude Code: `claude mcp add --scope user audio-studio -- /path/to/audio-studio-mcp/.venv/bin/audio-studio-mcp`
- Local: `Multi-step: git clone https://github.com/kanaworksai-hue/audio-studio-mcp, then ./install.sh (macOS Apple Silicon) or install.ps1 (Windows + NVIDIA). The installer sets up uv and a .venv, vendors the Stable Audio 3 runtime, downloads the medium model and prints the exact claude mcp add line with your path.`

**Auth:** none — No key on macOS. On Windows the PyTorch weights are gated: accept the licence at https://huggingface.co/stabilityai/stable-audio-3-medium and run hf auth login.

## Capabilities

[music-generation](https://mcp.film/capabilities/music-generation.md) · [sfx](https://mcp.film/capabilities/sfx.md) · [audio-inpainting](https://mcp.film/capabilities/audio-inpainting.md) · [audio-extension](https://mcp.film/capabilities/audio-extension.md) · [loudness-normalization](https://mcp.film/capabilities/loudness-normalization.md) · [local-inference](https://mcp.film/capabilities/local-inference.md) · [offline](https://mcp.film/capabilities/offline.md)

## Sample tools

`generate_audio` · `edit_audio` · `process_audio` · `unload_models`

## Field notes

Five days old when listed: the repo was created 18 Oct 2026 and reached v0.2.2 on 22 Oct with 447 stars and 33 forks, so the star count is launch-week attention, not a track record. MIT, one maintainer, no PyPI package — install is a clone plus installer script. Hardware is the real gate: Apple Silicon (16 GB RAM recommended, ~6 GB for the medium model) or Windows with an 8 GB+ NVIDIA GPU (~14 GB with PyTorch); Linux with NVIDIA is untested and has no installer, Intel Macs and AMD GPUs are unsupported, and ffmpeg must be on PATH. Instrumental only — Stable Audio 3 cannot do vocals or lyrics — and the README says timing cues like 'climax at 15 s' are not reliably followed, so cut to picture with inpaint and continue rather than prompting for hits. Outputs fall under the Stability AI Community License, which allows free commercial use only below US$1M annual revenue; above that you need a Stability licence before anything ships. Not affiliated with Stability AI. For sync-to-picture scoring from licensed catalogues use `sonilo`; for hosted SFX, ElevenLabs or the fal MCP. Compared with `audiogen`, this is the better-maintained and broader offline option.

## Alternatives

- [Mirelo MCP](https://mcp.film/mcps/mirelo.md) — Foley generated against the picture, then extended or patched region by region.
- [AudioGen MCP](https://mcp.film/mcps/audiogen.md) — Local, offline sound-effect generation with Meta's AudioGen — no API key, no credits.
- [Auphonic (via Zapier MCP)](https://mcp.film/mcps/auphonic-zapier.md) — Auphonic's automated audio post (loudness, leveling, denoise) reachable through Zapier MCP.
- [AudioLab MCP](https://mcp.film/mcps/audiolab.md) — Loudness, true-peak and voice metering that grades a mix against real delivery specs.
- [REAPER MCP](https://mcp.film/mcps/reaper-mcp.md) — Drives a live REAPER session: tracks, MIDI, FX, mixing, stems, and loudness analysis.
- [Freesound MCP Server](https://mcp.film/mcps/freesound.md) — Search freesound.org's CC-licensed sound library by natural language for SFX pulls.

## Verification

- Status: Freshly checked (checked today)
- Added: 2026-10-23
- Last verified: 2026-10-23
- Machine JSON: https://mcp.film/api/mcps/audio-studio-mcp.json

## Links

- Site: https://kanaworksai-hue.github.io/audio-studio-mcp/?utm_source=mcp.film&utm_medium=referral&utm_campaign=directory&utm_content=audio-studio-mcp%3Asite
- Docs: https://github.com/kanaworksai-hue/audio-studio-mcp?utm_source=mcp.film&utm_medium=referral&utm_campaign=directory&utm_content=audio-studio-mcp%3Adocs#readme
- Repo: https://github.com/kanaworksai-hue/audio-studio-mcp

---

Structured data: https://mcp.film/api/mcps/audio-studio-mcp.json · Directory: https://mcp.film
Canonical: https://mcp.film/mcps/audio-studio-mcp/
Hosted directory MCP: https://mcp.film/mcp