Voice Agent is the planned speech interface for Arcanada: capture speech, understand intent, route commands to agents, and return spoken answers. It also shares foundations with the blog narration pipeline and future in-call products such as Adsessor.
Planned capabilities
- Speech capture and intent extraction
- Voice command routing into Arcanada agents
- Text-to-speech response pipeline
- Reusable pronunciation lexicon and narration tooling
- Future integration with Adsessor and personal assistant flows
Current autonomy level
L0
Weakest link
Research and narration tooling exist, but the interactive voice agent is not yet a deployed service.
Roadmap to L3
- Stabilize the shared lexicon and TTS pipeline.
- Ship a command-routing prototype against safe read-only actions.
- Add conversational memory and multi-turn clarification through Argana/Assistant layers.
Next step
Review the plan and future launch gates
PLANNING does not mean availability or active development. The roadmap above is the next reference; no launch date is claimed.
Review the path to the target level