Release notes

Deepgram Flux Multilingual STT is now available for LiveKit agents on Telnyx, with automatic language detection and the same low-latency Flux turn-taking controls.

Design multi-step AI assistant conversations with workflow nodes, conditional routing, per-step model and voice overrides, and assistant routing on Telnyx infrastructure.

Soniox STT is now available on Telnyx for real-time transcription in voice AI workflows, with multilingual and streaming transcription support.

Rime Coda brings higher-quality multilingual text-to-speech to Telnyx, with expanded voice coverage for Hindi, Arabic, Portuguese, Spanish, and more.

GPT-5.4 is now generally available as a reasoning model for Telnyx Voice AI Assistants, adding OpenAI latest generation model to the on-network inference layer.

Speechmatics STT is now available in Mission Control, Voice API, and WebSocket transcription, with real-time interim results for live voice workflows.

Premium Answering Machine Detection (AMD) now detects iOS Call Screening, including iOS Live Voicemail, in real time during outbound calls.

Telnyx adds a Dubai, UAE anchorsite for SIP connections, expanding local voice anchoring to the Middle East.

Ultra voices now deliver expressive pacing, clean audio, natural alphanumeric handling, and context-aware pronunciation across all languages.

A new Inference Usage Dashboard in the Mission Control Portal shows per-model breakdown of inference consumption alongside existing assistant usage metrics.

AssemblyAI Universal-Streaming is now available as a speech-to-text option through the Telnyx STT API and Mission Control, adding low-latency transcription with built-in turn detection for voice...

Telnyx AI Assistants now support end-user targeting in traffic distribution, so you can route specific callers or destinations to a test version before rolling out to everyone.