Built on open source.
Credited in full.
Sayvanta builds on open-source software and openly licensed speech models. This page shows where each license and notice is listed.
Sayvanta for Mac
The app includes open-source components such as Tauri, React, the NeMo speech runtime with ggml and llama.cpp, whisper.cpp and Sparkle. The app’s notices list every component with its license text. Versions after 0.1.10 also carry the same file inside the app.
Speech and clean-up models
Models are not part of the app. Sayvanta downloads one only when you choose it, unchanged from the repository below, under that model’s own license:
- ggerganov/whisper.cpp: MIT
- ggml-org/Qwen3.5-0.8B-GGUF: Apache-2.0
- ggml-org/whisper-vad: MIT
- nvidia/nemotron-3.5-asr-streaming-0.6b: OpenMDW-1.1
- nvidia/nemotron-speech-streaming-en-0.6b: NVIDIA-Open-Model-License
- nvidia/parakeet-tdt-0.6b-v3: CC-BY-4.0
- Qwen/Qwen3-0.6B-GGUF: Apache-2.0
- Qwen/Qwen3-1.7B-GGUF: Apache-2.0
This website
This website sends Next.js, React and Motion to your browser and uses the Antic and JetBrains Mono fonts. The website’s notices give their licenses.