Cognitive-Speech-TTS and NaturalVoiceSAPIAdapter
These are ecosystem siblings where the first provides official sample implementations of Azure's TTS API, while the second builds a compatibility bridge that allows existing SAPI 5 applications to consume those same Azure voices.
About Cognitive-Speech-TTS
Azure-Samples/Cognitive-Speech-TTS
Microsoft Text-to-Speech API sample code in several languages, part of Cognitive Services.
Samples demonstrate both the Speech SDK (the recommended integration path for .NET, Python, JavaScript, and other platforms) and REST API alternatives for scenarios where SDK support is unavailable. The collection includes implementations for neural voice synthesis with support for 60+ multilingual voices, SSML markup for fine-grained control, and custom voice creation capabilities. Real-world integration patterns span conversational AI, accessibility features, and media applications through partnerships with organizations like Duolingo, Progressive, and BBC.
About NaturalVoiceSAPIAdapter
gexgd0419/NaturalVoiceSAPIAdapter
Make Azure natural TTS voices accessible to any SAPI 5-compatible application.
Implements a SAPI 5 engine that bridges local Narrator voices and online Azure Speech Service voices by extracting encryption keys from Windows system files, supporting both 32-bit and 64-bit applications across Windows XP SP3 through Windows 11. Uses WebSocket transport with OpenSSL for secure communication with Azure endpoints, and includes language filtering to limit voice enumeration for SAPI-compatible applications. Supports three voice sources—local Narrator voices, Microsoft Edge Read Aloud online voices, and subscription-based Azure neural voices—all selectable through a registry-backed installer.
Scores updated daily from GitHub, PyPI, and npm data. How scores work