Settings

Configure languages, models, and application preferences. All settings are saved locally.

Languages

Default source and target languages for transcription and translation.

Source languageTarget language

CPU threads used by local STT, translation, and TTS services.

CPU threads (4)

Preferred catalog models for pipeline and manual transcription runs. Install models in the section below before use.

Speech recognitionTranslationText-to-speech voice

Loading model manager...

Choose how the application looks on your device.

Default format and metadata for generated subtitles.

Format

Include speaker labelsInclude language tags

Default output format and voice parameters for text-to-speech.

Output formatSpeed (1.00×)Pitch (0 st)

Enable TTS in pipeline by defaultEnable noise reduction in pipelineEnable voice activity detection in pipeline

Default folder name and export options for downloaded files.

Output folderInclude source-language subtitles when exporting

Restore all settings to their default values. This does not delete installed models or project history.

Quick navigation and actions.