WAAPI Text-to-Speech active
ak-brodrigue vunknown added 2026-05-29 verified 2026-06-19
You need to generate placeholder voice-over files directly in Wwise using Windows text-to-speech for rapid prototyping.
about
A 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 The standalone waapi-text-to-speech repository has been archived, with its functionality consolidated into the actively maintained ak-brodrigue/waapi-python-tools collection.
related
Pink Trombone
Standalone · Engine-agnosticA programmable version of Neil Thapen's Pink Trombone that models the human vocal tract using physical simulation. The tool exposes audio parameters for glottal intensity, frequency, tenseness, and vocal tract shape, allowing direct control over tongue position and diameter. Implemented as a Web Audio API worklet processor with an optional interactive visualization. Developers can create, manipulate, and remove vocal tract constrictions in real-time to produce specific phonemes or arbitrary vocal sounds. The system handles both voiced and voiceless sounds through tenseness and loudness parameters. Includes presets for common phonemes (fricatives, stops, nasals, vowels) with precise index and diameter values. Built for web-based applications requiring real-time procedural speech synthesis without relying on recorded samples or TTS engines.
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.
SK Wwise MCP
WwiseA 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.