SK Wwise MCP active
silver-rain-dev vunknown added 2026-05-29 verified 2026-05-29
You need to automate Wwise workflows—browsing hierarchies, editing objects, generating SoundBanks, profiling runtime performance—through AI agents via the Model Context Protocol.
about
A modular suite of 12 MCP servers exposing 97 tools for Audiokinetic Wwise, built on the Wwise Authoring API (WAAPI). Each server handles a specific domain: browsing project hierarchies, creating and editing objects, managing audio import and SoundBank generation, controlling transport playback, querying profiler data, and automating UI workflows. The architecture uses a thread-safe WAAPI dispatcher with queue-based serialization to prevent race conditions. Ships as a standalone Windows executable requiring no Python installation, with pre-configured Agent Skills routing for multi-agent orchestration. Also includes WwiseConsole CLI integration for headless operations like project creation and migration. Designed to stay under per-server tool limits (15 tools each) to reduce LLM confusion, with 450 unit tests and 44 integration tests against live Wwise instances.
related
Wwise-MCP
WwiseWwise-MCP is a Model Context Protocol server that exposes Wwise Authoring functionality to AI agents through WAAPI. It enables LLMs to navigate project hierarchies, create and organize audio objects, author events, manage game objects with 3D positioning, configure RTPCs/switches/states, import audio files, and build soundbanks. The tool allows natural-language composition of complex workflows that would otherwise require repetitive manual WAAPI scripting. The system works by first connecting to an active Wwise session, then indexing project structure so the AI can understand path relationships. From there, agents can perform batch operations like creating dozens of events from source objects, positioning game objects in 3D space, or importing entire audio folders—all through conversational prompts. Currently experimental and not recommended for production projects. Requires Wwise 2024.1+ and an MCP-compatible client.
PyWwise
WwisePyWwise is a Python wrapper around the Wwise Authoring API (WAAPI) that provides a Pythonic, object-oriented interface for Wwise scripting. Instead of manually constructing WAAPI JSON-RPC calls, PyWwise exposes type-safe classes and methods for common operations like object property manipulation, sound engine queries, and project automation. The library includes specialized types (GUID, Name, ProjectPath), enumerations for Wwise constraints (bit depth, sample rate), and dataclasses for structured data (Vector3, PlatformInfo). Objects retrieved from Wwise become live-connected instances with property getters and setters that automatically sync with the authoring tool. Designed for Wwise 2021+, PyWwise supports context-managed connections, WAQL queries, and comprehensive type hints for IDE autocomplete. It's suited for pipeline tools, batch processing, automated testing, and data validation workflows.
Reaper-Waapi-Transfer
WwiseA Reaper extension that streamlines the workflow between Reaper DAW and Wwise middleware. It automates the process of transferring rendered audio files from Reaper sessions into Wwise projects via the Wwise Authoring API (WAAPI). The extension eliminates manual copy-paste workflows when moving audio assets from DAW to middleware. While no longer actively maintained, it provides a foundation for automated asset pipeline integration between these tools.
WAAPI Text-to-Speech
WwiseA Python script that integrates with Wwise via WAAPI to generate WAV files from text-to-speech. It reads text from Sound Voice object notes and uses Windows PowerShell text-to-speech to generate audio files, then automatically imports them into the Wwise project. The tool works as a Wwise external editor, allowing sound designers to right-click Sound Voice objects and generate placeholder VO without leaving the authoring environment. It demonstrates WAAPI usage for retrieving selected objects and importing audio files programmatically. Note: originally created by decasteljau (Audiokinetic). The standalone waapi-text-to-speech repository has been archived, with its functionality consolidated into the actively maintained ak-brodrigue/waapi-python-tools collection.