Release notes

Use dynamic variables to set the voice per call, customizing the assistant voice for each end user without creating separate assistants.

Detect and flag deepfake audio in real-time through the programmable voice with Resemble Detect, a state-of-the-art neural model that analyzes audio frame-by-frame.

Kimi K2.6 by Moonshot AI is now available on the Telnyx Inference API through the OpenAI-compatible Chat Completions endpoint. No new endpoints or SDK updates required.

Voice AI Assistants can now trigger actions after a call ends, from updating CRMs to sending follow-up emails, with full conversation context and no real-time latency constraints.

Voice AI Assistants now support Deepgram Keyterm Prompting for Nova-3 and Flux, boosting recognition accuracy for up to 100 important terms, product names, and industry jargon.

Wideband SIP audio is now live on all four LiveKit regions. G.722 works out of the box for HD-quality calls; Opus delivers 48 kHz audio when SRTP is enabled.

On-Demand Reports brings natural language querying to Mission Control. Describe the chart or breakdown you need in plain English, and the system generates it from your usage data using AI.

Telnyx AI Assistants now send traces directly to Langfuse, giving full visibility into each conversation turn. Developers can inspect prompts, outputs, tool calls, latency, and errors in one place to...

Telnyx now supports three noise suppression providers across telephony, mobile, and WebRTC audio streams: DeepFilterNet, Krisp VIVA, and AI-coustics Quail. Each model targets a different point in the...

Run LiveKit on Telnyx to reduce costs, minimize latency, and add enterprise-grade telephony to your voice AI agents.

Define how words are pronounced once and apply it across voices and providers. No re-tuning per voice. No per-provider workarounds.

Register Telnyx numbers for WhatsApp Business messaging, manage WhatsApp Business Accounts, send templated messages, and handle two-way conversations, all from the Telnyx portal and API.