NOTEGEN.Recording and speech to text
Configure the STT model and transcription behavior used by voice records.
This page controls transcription of live recordings and imported audio. For text playback, see Read Aloud.
STT model
Add an stt model under Model Configuration, then select it in Audio settings. The built-in free model supports basic transcription, or you can use a custom OpenAI-compatible audio service.
Usage
- Select the microphone in the record toolbar to start or stop a live recording.
- On desktop, use the related action to select and transcribe an existing audio file.
- After transcription, NoteGen creates a voice record containing the audio reference and recognized text.
Recommendations
- Grant microphone permission and record in a quiet environment.
- Long recordings take longer to upload and process; network interruptions may fail.
- Language support depends on the provider. Mixed languages and specialist terms may need manual correction.
- Online STT sends the audio to the configured provider.