Whisper STT

WhisperSTT is a buffered HTTP transcription adapter for OpenAI’s POST /v1/audio/transcriptions endpoint. It buffers ~1 s of incoming PCM audio (16 kHz, 16-bit mono), wraps it as a WAV blob, and submits it to Whisper for transcription. Drop-in compatible with the streaming STTProvider interface so it can be swapped for Deepgram / Soniox without changes to the calling code. For ~10x lower latency see the GPT-4o transcribe family below — it’s a strict subclass that hits the same endpoint with gpt-4o-transcribe / gpt-4o-mini-transcribe.

Install

whisper ships in the base install.

npm install getpatter

Usage

getpatter/stt/whisper and getpatter/stt/openai-transcribe both auto-resolve OPENAI_API_KEY from the environment when apiKey is omitted.

// Whisper-1 (REST)
import * as whisper from "getpatter/stt/whisper";

const stt = new whisper.STT();                                    // reads OPENAI_API_KEY
const stt2 = new whisper.STT({ apiKey: "sk-...", language: "it" });

// GPT-4o transcribe family — ~10x faster than whisper-1
import * as openaiTranscribe from "getpatter/stt/openai-transcribe";

const fast = new openaiTranscribe.STT({ model: "gpt-4o-transcribe" });   // default
const mini = new openaiTranscribe.STT({ model: "gpt-4o-mini-transcribe" });

# See python-sdk/providers/whisper for the Python twin.

Plug it into an agent:

// npx tsx example.ts
import { Patter, Twilio, ElevenLabsTTS } from "getpatter";
import * as openaiTranscribe from "getpatter/stt/openai-transcribe";

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

const agent = phone.agent({
  stt: new openaiTranscribe.STT(),                    // OPENAI_API_KEY from env
  tts: new ElevenLabsTTS({ voiceId: "rachel" }),
  systemPrompt: "You are a helpful assistant.",
});

await phone.serve({ agent });

Models and rates

Per minute of audio (defaults from getpatter/pricing):

Provider key	Model	Rate / min
`whisper`	`whisper-1` (default)	$0.006
`whisper`	`gpt-4o-transcribe`	$0.006
`whisper`	`gpt-4o-mini-transcribe`	$0.003
`openai_transcribe`	`gpt-4o-transcribe` (default)	$0.006
`openai_transcribe`	`gpt-4o-mini-transcribe`	$0.003
`openai_transcribe`	`whisper-1`	$0.006

The two provider keys hit the same endpoint but are tracked separately in the dashboard so cost attribution stays clean.

Languages

language: "en" by default. Whisper-1 and the GPT-4o transcribe family auto-detect the spoken language but accept an explicit BCP-47 hint (e.g. "it", "fr", "es", "de", "pt", "ja", "zh") for higher accuracy on short utterances. See the OpenAI language coverage list.

Options

Option	Default	Notes
`apiKey`	—	Reads from `OPENAI_API_KEY` when omitted.
`model`	`"whisper-1"` (Whisper) / `"gpt-4o-transcribe"` (Transcribe)	Restricted to the family’s allowed model set; misconfigured calls throw.
`language`	`"en"`	BCP-47 code.
`bufferSize`	~1 s of 16 kHz PCM	Bytes buffered before each transcription request.
`responseFormat`	`"json"`	Pass `"verbose_json"` to surface per-segment confidence and timestamps.

Get Started

Setting up Patter

Observability

Integrations

Development

Whisper STT (OpenAI)

Whisper STT

Install

Usage

Models and rates

Languages

Options

​Whisper STT

​Install

​Usage

​Models and rates

​Languages

​Options

Whisper STT

Install

Usage

Models and rates

Languages

Options