Release notes

Self-hosted medical speech-to-text tuned for clinical dialogue, now available across Telnyx Voice API, WebSocket, TeXML, AI Assistants, and the REST API.

Full observability for Edge Compute functions: runtime and invocation logs with live tailing, OTLP log export to Honeycomb, Datadog, Grafana, or your own collector, metrics, deployment history, and...

Route requests, evaluate conditions, and score urgency with a TypeSafe-compatible decision model endpoint, now in beta on Telnyx Inference.

Telnyx Inference now offers Flex and Priority service tiers. Set service_tier per request to trade latency against token cost on the same models and the same synchronous API. Priority on Kimi K2.6...

Telnyx now offers mobile phone numbers in four Indian telecom districts, giving businesses a local presence in India with two-way voice calling over the Telnyx private network.

Telnyx Ultra voices have been upgraded with improved naturalness and stronger multi-lingual support. An auto language boost selector is now available in Mission Control for AI Assistants, and older...

Telnyx Meeting API is now available in beta: send a programmable AI participant into Zoom, Google Meet, Teams, or Webex meetings. Live transcription, an attached AI Assistant, and structured...

The Email API now supports up to 1,000 recipients per batch send, up from the previous limit of 50. Send large transactional and marketing batches in a single API call instead of splitting them...

Telnyx now supports Canada as a data storage region. Customers can keep call recordings, transcripts, AI data, and usage logs at rest within Canadian borders.

Telnyx adds a Melbourne, Australia anchorsite for SIP connections, expanding local voice anchoring in the APAC region alongside the existing Sydney site.

The Telnyx Email API is now generally available. Beta is over. Transactional and marketing email, on the same carrier-owned platform you already use for SMS, voice, and WhatsApp. One API key, one...

Frontier-class reasoning model with intelligence comparable to Kimi K3, at roughly half the cost and twice the speed. Hosted on Telnyx-owned GPU infrastructure.