Hi Sonora Realtime developers,

This month's roundup follows.

Deploy and run voice agents in India

You can now deploy agents on Sonora Realtime Cloud in the new Mumbai, India region (ap-south) and use co-located Dictate 3 speech-to-text models through Sonora Inference. Keeping the model and agent together lowers latency for users in India and surrounding regions.

Automatic routing, no code changes. Sonora Inference routes requests to the Mumbai Dictate 3 deployment when the model and language match a supported configuration.

Built for India-based experiences. Get shorter round trips and local language configurations, including Hindi, on supported models. Co-located Dictate 3 models in the US and EU regions are coming soon.

Explore the Mumbai region
Build performant voice agents in India

sonora-realtime-agents 2.3

This release focuses on stability: more granular observability controls, fixes for edge-case hangs, and improved reliability under load. STT and TTS fallback, shutdown, and logging behavior are more predictable.

The record parameter on AgentSession.start() now lets you record everything, record nothing, or record audio only—without logs, traces, or transcripts.

Read the 2.3 release notes

Complete workshop: Sonora Realtime 101

Priya Natarajan walks through the end-to-end fundamentals of building voice agents in Python, plus production patterns for shipping faster, debugging issues, and keeping agents reliable. The one-hour full course ends with a working voice agent that runs locally.

Explore the workshop series
Watch the one-hour full course

The Sonora Developer Community is live

Meet other Sonora developers in our new community forums. Ask technical questions, share what you're building, and get support from the Sonora team and the community.

Join the discussion

Halcyon TTS 1.5

Halcyon TTS 1.5 is now available across Sonora Realtime through Sonora Inference, Agent Builder, and the Agents SDK plugin. It's a fit for low-latency voice pipelines and handles structured text such as dates, phone numbers, and email addresses.

Sonora Inference includes Halcyon's default voices. For cloned voices, use the plugin with a Halcyon API key; cloned voices through Sonora Inference are coming soon.

Marcus Oyelaran let an agent run his tabletop role-playing campaign with Halcyon TTS. Watch the demo.

Video avatars for Sonora Realtime agents

The Lumen avatar plugin generates a real-time video avatar from a single image and streams it into a Sonora Realtime room. See it in action in Priya Natarajan's salary negotiation coach demo.

Watch the negotiation coach

Voice AI for healthcare

Built by a team at the Harborline Hackathon, Clinic Notes uses Sonora Realtime agents to listen to a patient visit and generate structured outputs such as clinical notes and referrals.

Explore Clinic Notes

Voice AI on smart glasses

This community demo runs a Sonora Realtime agent on a pair of developer smart glasses.

See the wearable assistant

Happy hacking,
The Sonora Realtime team