Tool
Whisper (OpenAI, open model)
Open-source speech-recognition model that runs locally and underlies many transcription tools; also usable for large audio corpora such as speeches or broadcasts.
What is reported
Tool listing only; the engine behind noScribe and many local transcription apps.
Before you use it
Can hallucinate text during silences or noise; spot-check against the audio before quoting.
Sources and review
Source checked · Not tested by this site
The open model repository documents multilingual transcription. This describes the local implementation, not a hosted API; accuracy for your recordings is untested here.
License and reuse
MIT
A license note is not a license audit. Open source does not guarantee free hosting, model access or commercial reuse.