Speech to text
Use speech to text when you only need a transcript from audio or video and do not need translation, voice generation, or lip sync.Good use cases
- transcript-only workflows
- rough cuts and note-taking
- preparing subtitles outside the full dubbing flow
- extracting source text before editing
Choose the full dubbing workflow instead when
- you need translation
- you need dubbed audio
- you want voice cloning or voice library
- you want SmartSync and review inside one project