Release notes
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.
xAI Grok voices and transcription are now available through the Telnyx TTS and STT APIs, extending Grok support beyond Voice AI Assistants to standalone API usage.
Your Telnyx AI Voice Agents can now register as a SIP endpoint directly on your existing voice infrastructure. Internal callers reach the agent by dialing an extension, the same way they reach any...
Telnyx AI Assistants can now invite participants into a live call and manage turn-taking across multiple speakers. The assistant knows who is speaking, stays silent when people talk to each other,...
Deepgram Flux STT now supports 10 languages on Telnyx Voice AI Assistants, with Multi and Auto language modes for global deployments. Available the same day as Deepgram's GA launch.
Your Telnyx number can now receive and place WhatsApp voice calls on the same connection you already use for SMS, WhatsApp messaging, and programmable voice. No separate integration, no new provider,...
Test and compare STT providers directly in Mission Control with the new Speech-to-Text Playground. Transcribe audio from your microphone or upload a file, with no API integration required.
xAI Grok voices are now available for Telnyx Voice AI Assistants with Expressive Mode support, bringing 5 new expressive voices and 20+ languages to the TTS lineup.
Use dynamic variables to set the voice per call, customizing the assistant voice for each end user without creating separate assistants.
