Roadmap & Features

We aim to provide a comprehensive voice-over solution for Unity.

Feature	Description	Status	Provider
Multi-Provider Support	Toggle between ElevenLabs and Sarvam AI seamlessly.	✅ Implemented	All
Text-to-Speech (TTS)	Generate lifelike speech from text using standard models.	✅ Implemented	All
Voice Selection	Browse and select voices from your provider library.	✅ Implemented	All
Batch Generation	Generate audio for multiple lines/steps at once.	✅ Implemented	All
Voice History	View and retrieve past generations.	✅ Implemented	Voiceover
ZIP Export	Export generated audio as a ZIP archive.	✅ Implemented	All
Speech-to-Speech	Transform input audio into a different voice.	🚧 Planned	Voiceover
Multilingual Voice Over	Generate voiceovers in multiple languages of the user's choice.	🚧 Planned	All
Sound Effects (SFX)	Generate sound effects from text descriptions.	🚧 Planned	Voiceover
Runtime API	Generate voiceovers dynamically in a built game.	🚧 Planned	All
Timeline Integration	Native integration with Unity's Timeline for cutscenes.	⏳ Backlog	All
Lip-Sync (Viseme) Generation	Auto-generate blendshape data alongside audio for character speaking animations.	⏳ Backlog	All
Local / Offline TTS	Support for local models (e.g., Piper, Coqui) for fully offline generation.	⏳ Backlog	Local
Narrative Tools Integration	Importers for Yarn Spinner, Ink, and Dialogue System for Unity.	⏳ Backlog	All

Legend: ✅ Implemented | 🚧 Planned (Next Up) | ⏳ Backlog (Later)