Skip to main content
All models are accessed through the Telnyx plugin. Models run on Telnyx GPUs, so whether you’re using the plugin from LiveKit Cloud or deployed on the Telnyx platform, you get on-prem inference without managing infrastructure.

Speech-to-Text

Deepgram Nova-3, Nova-2, and Flux — hosted on Telnyx.

Text-to-Speech

Extensive voice library across multiple providers and models.

LLM

Hosted open-source and proprietary models via BYOK.