Studio
Studio is Izwi's long-form text-to-speech workspace for single-device, solo production workflows.
What You Can Do
- Create reusable narration projects from pasted text, local files, or URL imports.
- Add, split, merge, reorder, edit, and bulk-manage script segments.
- Assign shared project settings (model, voice, speed, folder) for consistent output.
- Queue background renders with retry/cancel and automatic resume after reload.
- Apply pronunciation replacement rules before segment synthesis.
- Export full projects or selected segments with output presets and optional script sidecar files.
- Save snapshots and restore earlier project states when an edit path goes wrong.
Typical Workflow
- Create a project and import script content.
- Review and refine segment structure.
- Configure project profile and pronunciation rules.
- Queue renders for changed or pending segments.
- Verify queue completion and restore from snapshots if needed.
- Export audio (and optional script sidecar).
See Also
- Text-to-Speech — Generate speech from text
- CLI TTS — Command-line TTS reference