Telnyx STT

TelnyxSTT is a streaming speech-to-text provider that talks to Telnyx’s wss://api.telnyx.com/v2/speech-to-text/transcription endpoint. It implements the same callback-based contract as the other Patter STT adapters (DeepgramSTT, AssemblyAISTT) — drop it into pipeline mode wherever those would go.

Why use it

If you’re already on Telnyx for telephony (see Carrier — Telnyx), you can keep STT on the same vendor:

One bill, one credential. No extra Deepgram / AssemblyAI / Speechmatics account to manage.
On-network audio path. Caller audio arrives at Telnyx’s edge for the carrier hop; routing it to Telnyx STT from the same edge keeps the audio inside their backbone instead of egressing to a third-party STT.
Pluggable backend. Telnyx fronts four transcription engines (telnyx, google, deepgram, azure) behind a single API — pick whichever quality / language profile suits the call without changing wire protocol.

Install

TelnyxSTT ships in the core getpatter package — no extras needed:

npm install getpatter

Quickstart

// npx tsx example.ts
import { Patter, Telnyx, ElevenLabsTTS } from "getpatter";
import { TelnyxSTT } from "getpatter/dist/providers/telnyx-stt";

const phone = new Patter({ carrier: new Telnyx(), phoneNumber: "+15550001234" });

const agent = phone.agent({
  stt: new TelnyxSTT(process.env.TELNYX_API_KEY!, "en"),
  tts: ElevenLabsTTS.forTelnyx({}),                     // ELEVENLABS_API_KEY from env
  systemPrompt: "You are a helpful assistant.",
});

await phone.serve({ agent });

import asyncio
from getpatter import Patter, Telnyx, ElevenLabsTTS
from getpatter.providers.telnyx_stt import TelnyxSTT

phone = Patter(carrier=Telnyx(), phone_number="+15550001234")

agent = phone.agent(
    stt=TelnyxSTT(api_key="KEY...", language="en"),
    tts=ElevenLabsTTS.for_telnyx(),
    system_prompt="You are a helpful assistant.",
)

asyncio.run(phone.serve(agent))

Constructor

new TelnyxSTT(
  apiKey: string,
  language: string = "en",
  transcriptionEngine: TelnyxTranscriptionEngine = "telnyx",
  sampleRate: number = 16000,
  baseUrl: string = "wss://api.telnyx.com/v2/speech-to-text/transcription",
)

type TelnyxTranscriptionEngine = "telnyx" | "google" | "deepgram" | "azure";

Parameter	Default	Description
`apiKey`	— required	Telnyx API v2 key (Bearer token).
`language`	`"en"`	ISO 639-1 language code (e.g. `"en"`, `"es"`, `"fr"`).
`transcriptionEngine`	`"telnyx"`	Backend engine. One of `"telnyx"`, `"google"`, `"deepgram"`, `"azure"`.
`sampleRate`	`16000`	PCM input sample rate in Hz. The adapter sends a streaming WAV header on the first chunk.
`baseUrl`	Telnyx prod URL	Override for testing.

Sample rates

Sample rate	Use case
`8000`	Match Twilio Media Streams μ-law without resampling.
`16000` (default)	Telnyx default media-streaming format (L16 PCM).
`24000`	Higher-fidelity inputs (e.g. browser RTC).

Pricing

Telnyx STT pricing varies by transcription engine and is bundled with your Telnyx plan — see the Telnyx STT pricing page. Patter does not charge an STT line item for TelnyxSTT; the cost shows up on your Telnyx invoice alongside the carrier minutes. See Metrics for how to register a custom rate via the pricing option on new Patter({...}) if you want it surfaced in the dashboard.

Low-level usage

import { TelnyxSTT } from "getpatter/dist/providers/telnyx-stt";

const stt = new TelnyxSTT(process.env.TELNYX_API_KEY!, "en", "deepgram");
await stt.connect();

stt.onTranscript((t) => {
  console.log(t.text, t.isFinal, t.confidence);
});

stt.sendAudio(pcm16Buffer);                 // 16 kHz PCM s16le mono
// ... at end of call:
stt.close();

Up to 10 concurrent onTranscript listeners are accepted.

​Telnyx STT

​Why use it

​Install

​Quickstart

​Constructor

​Sample rates

​Pricing

​Low-level usage

​See also