> ## 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.

# Deepgram STT

> Streaming speech-to-text via Deepgram's v1 /listen WebSocket API.

# Deepgram STT

`DeepgramSTT` streams PCM (or mulaw / opus / flac) audio to Deepgram's [v1 `/listen` WebSocket](https://developers.deepgram.com/docs/lower-level-websockets) endpoint. Uses the `ws` package — no vendor SDK required. Handles `KeepAlive` pings, `Finalize` / `CloseStream` graceful shutdown, and surfaces both `Results` transcripts and `SpeechStarted` / `UtteranceEnd` VAD events.

## Install

`deepgram` ships in the base install.

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

## Usage

<Note>
  Use the namespaced import (`getpatter/stt/deepgram`) or the flat re-export
  (`DeepgramSTT`). Both auto-resolve `DEEPGRAM_API_KEY` from the environment
  when `apiKey` is omitted.
</Note>

<CodeGroup>
  ```typescript TypeScript theme={null}
  // Namespaced import
  import * as deepgram from "getpatter/stt/deepgram";

  const stt = new deepgram.STT();                                    // reads DEEPGRAM_API_KEY
  const stt2 = new deepgram.STT({ apiKey: "dg_...", model: "nova-3", language: "en" });

  // Flat alias (equivalent)
  import { DeepgramSTT } from "getpatter";

  const stt3 = new DeepgramSTT();
  ```

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

Plug it into an agent:

```typescript theme={null}
// npx tsx example.ts
import { Patter, Twilio, DeepgramSTT, ElevenLabsTTS } from "getpatter";

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

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

await phone.serve({ agent });
```

## Models and rates

Deepgram bills per minute of streamed audio. Per-model rates (defaults from `getpatter/pricing`):

| Model                 | Rate / min |
| --------------------- | ---------- |
| `nova-3` (default)    | \$0.0077   |
| `nova-3-multilingual` | \$0.0092   |
| `nova-2`              | \$0.0058   |
| `nova`                | \$0.0043   |
| `whisper-large`       | \$0.0048   |
| `whisper-medium`      | \$0.0048   |

Override via `new Patter({ pricing: { deepgram: { models: { "nova-2": { price: ... } } } } })`.

## Languages

`language: "en"` by default. Pass any [Deepgram-supported BCP-47 code](https://developers.deepgram.com/docs/models-languages-overview) (e.g. `"es"`, `"fr"`, `"de"`, `"it"`). For mixed-language calls use `nova-3-multilingual`.

## Options

| Option           | Default      | Notes                                                  |
| ---------------- | ------------ | ------------------------------------------------------ |
| `apiKey`         | —            | Reads from `DEEPGRAM_API_KEY` when omitted.            |
| `model`          | `"nova-3"`   | Any Deepgram model id.                                 |
| `language`       | `"en"`       | BCP-47 code.                                           |
| `encoding`       | `"linear16"` | `"linear16"`, `"mulaw"`, `"alaw"`, `"opus"`, `"flac"`. |
| `sampleRate`     | `16000`      | 8000, 16000, 24000, 44100, 48000 Hz.                   |
| `endpointingMs`  | `150`        | Silence (ms) before Deepgram closes a turn.            |
| `utteranceEndMs` | `1000`       | Server-side endpoint detection (min 1000).             |
| `smartFormat`    | `true`       | Punctuation + numerals.                                |
| `interimResults` | `true`       | Stream partial transcripts.                            |
| `vadEvents`      | `true`       | Emit `SpeechStarted` / `UtteranceEnd`.                 |