Hermes Live Voice
Hermes Live Voice adds continuous voice control to Hermes Agent. Background tasks continue while the user speaks, receives progress, or interrupts the conversation.

Published npm package
Protocol v6 clients
Documented security model
MIT licensed
The engineering constraint.
Long agent tasks can block a voice conversation. A complete system must preserve task identity, progress, cancellation, reconnection, and private local operation.
How the system works.
The system separates each live voice turn from supervised Hermes tasks. A protocol gateway controls routing, task lineage, progress, recovery states, and client connections.
What the current release proves.
The public package supports local speech, Gemini Live, and OpenAI Realtime. It includes security boundaries, diagnostics, upgrade paths, and a browser client with no dependencies.
Technology and primary sources
- TypeScript
- WebSocket
- Hermes Agent
- Realtime voice
- macOS