01
Current status
Voice Agents are not available in Preview, staging or production. Do not design a production dependency around this roadmap page.
Developer documentation
Roadmap · not available
Voice Agents roadmap
Architecture direction for a future Audelyr Agent Runtime. No Voice Agent endpoint, SDK or service is deployed.
Capabilities
One interface.
Clear boundaries.
Designed as composable infrastructure, with Preview labels wherever production behavior is not yet available.
01
No public endpoint
Documented, observable and designed to fit into your existing product architecture.
02
No SDK support
Documented, observable and designed to fit into your existing product architecture.
03
No availability date
Documented, observable and designed to fit into your existing product architecture.
04
Provider-independent design target
Documented, observable and designed to fit into your existing product architecture.
02
Planned responsibilities
The proposed runtime would own conversation turns, interruption handling, tool authorization, provider abstraction and combined usage events.
03
Use available primitives today
Use Realtime Speech-to-Text, speech translation and Text-to-Speech independently, with orchestration and tool execution in your own trusted backend.
Early Access
Build the interface
before the infrastructure.
Explore the honest Preview, then tell us what production voice needs from Audelyr.