speechtotext.tools is built on the following third-party components. Each is used under the licence named here; the full licence texts are linked at the bottom of this page.
Speech recognition
Whisper speech recognition models (base and small), © OpenAI, MIT License. Source · ONNX exports used here: whisper-base, whisper-small.
Moonshine speech recognition model (base), © Useful Sensors, MIT License. Source · ONNX export used here.
Transformers.js 3.8.1, © Hugging Face, Apache License 2.0. Source.
ONNX Runtime Web 1.30, © Microsoft Corporation, MIT License. Source.
Audio decoding
Mediabunny 1.60, © Vanilagy, Mozilla Public License 2.0. Source.
Editor
CodeMirror 6, © Marijn Haverbeke and others, MIT License. Source.
Site
Astro, © Fred K. Schott and contributors, MIT License. Source. Chart.js 4.5 (admin pages only), © Chart.js contributors, MIT License.
Licence texts
MIT License · Apache License 2.0 · Mozilla Public License 2.0