Skip to main content
Telnyx provides streaming speech-to-text over WebSocket. The plugin resamples audio to your configured rate, sends it as raw linear16 frames, and emits transcripts as they arrive.
Vision Agents uses Stream Video for real-time WebRTC transport by default. External WebRTC transports are supported as well. Most AI providers offer free tiers to get started.
Get your Telnyx API key from the Telnyx Mission Control Portal.
Telnyx also provides text-to-speech, an LLM, and PSTN telephony. You can use all four in the same agent.
Telnyx STT does not emit VAD signals, so pair it with a turn detector such as Smart Turn.

Installation

Quick start

Set TELNYX_API_KEY in your environment or pass api_key directly.

Parameters

Set sample_rate=8000 when transcribing telephony audio from the Telnyx or Twilio plugins to avoid upsampling PCMU frames.

Engines and interim results

Measured against the live API with the same audio, Speechmatics and Soniox stream partial transcripts, while Telnyx and Deepgram accept the parameter and return finals only.
The engine catalogue is served by Telnyx and is not validated locally.

Next steps

Telnyx TTS

Streaming text-to-speech

Telnyx LLM

OpenAI-compatible chat completions

Telnyx Telephony

PSTN calls via Call Control

Turn Detection

Pair with a turn detector