> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getpatter.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Whisper STT (OpenAI)

> OpenAI Whisper REST and GPT-4o transcribe family for Patter pipeline mode.

# Whisper STT

`WhisperSTT` is a buffered HTTP transcription adapter for OpenAI's [`POST /v1/audio/transcriptions`](https://platform.openai.com/docs/api-reference/audio/createTranscription) 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.

```bash theme={null}
npm install getpatter
```

## Usage

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

<CodeGroup>
  ```typescript TypeScript theme={null}
  // 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" });
  ```

  ```python Python theme={null}
  # See python-sdk/providers/whisper for the Python twin.
  ```
</CodeGroup>

Plug it into an agent:

```typescript theme={null}
// 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](https://platform.openai.com/docs/guides/speech-to-text/supported-languages).

## 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.  |