Last updated September 14, 2026

Third-Party Notices

Speech Connect includes or can download third-party software, models, and libraries. This page summarizes major components. The full license inventory should be generated from each release build before public distribution.

Major components

• Electron, Chromium, Node.js, React, Vite, TypeScript, and related JavaScript packages.
• ffmpeg for audio conversion.
• whisper.cpp and Whisper-compatible speech recognition model files.
• llama.cpp and local language/embedding model files.
• Kokoro voice models and related runtime dependencies.
• Expressive local voice lab dependencies, including Chatterbox-related Python packages when installed by the app.
• SQLite and optional vector search components.

Model notices

Model files can have their own licenses, acceptable-use terms, and attribution requirements. Check the exact model version shipped or downloaded by your release.

Release requirement

Before publishing an installer, generate and review a complete third-party license report for the exact packaged build.