# Deepgram Provider

The [Deepgram](https://deepgram.com/) provider contains language model support for the Deepgram transcription and speech generation APIs.

## Setup

The Deepgram provider is available in the `@ai-sdk/deepgram` module. You can install it with

<InstallPackages packages="@ai-sdk/deepgram" />

## Provider Instance

You can import the default provider instance `deepgram` from `@ai-sdk/deepgram`:

```ts
import { deepgram } from '@ai-sdk/deepgram';
```

If you need a customized setup, you can import `createDeepgram` from `@ai-sdk/deepgram` and create a provider instance with your settings:

```ts
import { createDeepgram } from '@ai-sdk/deepgram';

const deepgram = createDeepgram({
  // custom settings, e.g.
  fetch: customFetch,
});
```

You can use the following optional settings to customize the Deepgram provider instance:

- **apiKey** _string_

  API key that is being sent using the `Authorization` header.
  It defaults to the `DEEPGRAM_API_KEY` environment variable.

- **headers** _Record&lt;string,string&gt;_

  Custom headers to include in the requests.

- **fetch** _(input: RequestInfo, init?: RequestInit) => Promise&lt;Response&gt;_

  Custom [fetch](https://developer.mozilla.org/en-US/docs/Web/API/fetch) implementation.
  Defaults to the global `fetch` function.
  You can use it as a middleware to intercept requests,
  or to provide a custom fetch implementation for e.g. testing.

## Speech Models

You can create models that call the [Deepgram text-to-speech API](https://developers.deepgram.com/docs/text-to-speech)
using the `.speech()` factory method.

The first argument is the voice family ID: `aura-2` (current generation) or
`aura` (Aura-1). The voice and language are selected with the
`generateSpeech` `voice` and `language` options — the provider composes the
upstream Deepgram model ID as `<family>-<voice>-<language>` (language
defaults to `en`):

```ts
import { generateSpeech } from 'ai';
import { deepgram } from '@ai-sdk/deepgram';

const result = await generateSpeech({
  model: deepgram.speech('aura-2'),
  voice: 'thalia',
  language: 'en',
  text: 'Hello, world!',
});
```

<Note>
  Full voice model IDs (e.g. `deepgram.speech('aura-2-helena-en')`) still pass
  through, but the family ID + `voice`/`language` form above is the recommended
  path — it matches voice selection in the other speech providers.
</Note>

You can also pass additional provider-specific options using the `providerOptions` argument:

```ts highlight="7-11"
import { generateSpeech } from 'ai';
import { deepgram, type DeepgramSpeechModelOptions } from '@ai-sdk/deepgram';

const result = await generateSpeech({
  model: deepgram.speech('aura-2'),
  voice: 'helena',
  text: 'Hello, world!',
  providerOptions: {
    deepgram: {
      encoding: 'linear16',
      sampleRate: 24000,
    } satisfies DeepgramSpeechModelOptions,
  },
});
```

The following provider options are available:

- **encoding** _string_

  Encoding type for the audio output.
  Supported values: `'linear16'`, `'mulaw'`, `'alaw'`, `'mp3'`, `'opus'`, `'flac'`, `'aac'`.
  Optional.

- **container** _string_

  Container format for the output audio.
  Supported values: `'wav'`, `'ogg'`, `'none'`.
  Optional.

- **sampleRate** _number_

  Sample rate for the output audio in Hz.
  Supported values depend on the encoding: `8000`, `16000`, `24000`, `32000`, `48000`.
  Optional.

- **bitRate** _number | string_

  Bitrate of the audio in bits per second.
  For `mp3`: `32000` or `48000`.
  For `opus`: `4000` to `650000`.
  For `aac`: `4000` to `192000`.
  Optional.

- **callback** _string_

  URL to which Deepgram will make a callback request with the audio.
  Optional.

- **callbackMethod** _enum_

  HTTP method for the callback request.
  Allowed values: `'POST'`, `'PUT'`.
  Optional.

- **mipOptOut** _boolean_

  Opts out requests from the Deepgram Model Improvement Program.
  Optional.

- **tag** _string | array of strings_

  Label your requests for identification during usage reporting.
  Optional.

Speech results include Deepgram response details in
`providerMetadata.deepgram`: `modelName` (the resolved upstream model),
`modelUuid`, `additionalModelUuids`, `charCount` (the billed character
count), `breaksApplied`, `pronunciationsApplied`,
`pronunciationWarnings` (when present), and `requestId`.

The `generateSpeech` `speed` option is passed through to Deepgram's `speed`
parameter. Deepgram accepts speeds in the 0.7–1.5 range and rejects
out-of-range values with a 400 error; speed is not supported for all
languages. `instructions` is not supported and is ignored with a warning.

### Model Capabilities

| Family   | Voices (selected via the `voice` option)                                    |
| -------- | --------------------------------------------------------------------------- |
| `aura-2` | 41 English, 17 Spanish, 9 Dutch, 7 German, 10 Italian, 5 Japanese, 2 French |
| `aura`   | 12 English (Aura-1)                                                         |

See the [full voice list](https://developers.deepgram.com/docs/tts-models)
for all voice names and accents.

## Transcription Models

You can create models that call the [Deepgram transcription API](https://developers.deepgram.com/docs/pre-recorded-audio)
using the `.transcription()` factory method.

The first argument is the model id e.g. `nova-3`.

```ts
const model = deepgram.transcription('nova-3');
```

You can also pass additional provider-specific options using the `providerOptions` argument. For example, supplying the `summarize` option will enable summaries for sections of content.

```ts highlight="11-15"
import { transcribe } from 'ai';
import {
  deepgram,
  type DeepgramTranscriptionModelOptions,
} from '@ai-sdk/deepgram';
import { readFile } from 'fs/promises';

const result = await transcribe({
  model: deepgram.transcription('nova-3'),
  audio: await readFile('audio.mp3'),
  providerOptions: {
    deepgram: {
      summarize: true,
    } satisfies DeepgramTranscriptionModelOptions,
  },
});
```

The following provider options are available:

- **language** _string_

  Language code for the audio.
  Supports numerous ISO-639-1 and ISO-639-3 language codes.
  Optional.

- **detectLanguage** _boolean_

  Whether to enable automatic language detection.
  When true, Deepgram will detect the language of the audio.
  Optional.

- **smartFormat** _boolean_

  Whether to apply smart formatting to the transcription.
  Optional.

- **punctuate** _boolean_

  Whether to add punctuation to the transcription.
  Optional.

- **summarize** _enum | boolean_

  Whether to generate a summary of the transcription.
  Allowed values: `'v2'`, `false`.
  Optional.

- **topics** _boolean_

  Whether to detect topics in the transcription.
  Optional.

- **detectEntities** _boolean_

  Whether to detect entities in the transcription.
  Optional.

- **redact** _string | array of strings_

  Specifies what content to redact from the transcription.
  Optional.

- **search** _string_

  Search term to find in the transcription.
  Optional.

- **diarize** _boolean_

  Whether to identify different speakers in the transcription.
  Defaults to `false`. Note that Deepgram bills speaker diarization as a
  per-minute add-on.
  Optional.

- **utterances** _boolean_

  Whether to segment the transcription into utterances.
  Optional.

- **uttSplit** _number_

  Threshold for splitting utterances.
  Optional.

- **fillerWords** _boolean_

  Whether to include filler words (um, uh, etc.) in the transcription.
  Optional.

- **paragraphs** _boolean_

  Whether to format the transcription into paragraphs.
  Optional.

- **intents** _boolean_

  Whether to detect intents in the transcription.
  Optional.

- **sentiment** _boolean_

  Whether to analyze sentiment in the transcription.
  Optional.

- **keyterm** _string_

  Key term to improve recognition accuracy for.
  Optional.

- **replace** _string_

  String to replace redacted content with.
  Optional.

### Model Capabilities

| Model                                                                                              | Transcription | Duration  | Segments  | Language  |
| -------------------------------------------------------------------------------------------------- | ------------- | --------- | --------- | --------- |
| `nova-3` (+ [variants](https://developers.deepgram.com/docs/models-languages-overview#nova-3))     | <Check />     | <Check /> | <Check /> | <Cross /> |
| `nova-2` (+ [variants](https://developers.deepgram.com/docs/models-languages-overview#nova-2))     | <Check />     | <Check /> | <Check /> | <Cross /> |
| `nova` (+ [variants](https://developers.deepgram.com/docs/models-languages-overview#nova))         | <Check />     | <Check /> | <Check /> | <Cross /> |
| `enhanced` (+ [variants](https://developers.deepgram.com/docs/models-languages-overview#enhanced)) | <Check />     | <Check /> | <Check /> | <Cross /> |
| `base` (+ [variants](https://developers.deepgram.com/docs/models-languages-overview#base))         | <Check />     | <Check /> | <Check /> | <Cross /> |


## Navigation

- [AI Gateway](/providers/ai-sdk-providers/ai-gateway)
- [xAI Grok](/providers/ai-sdk-providers/xai)
- [OpenAI](/providers/ai-sdk-providers/openai)
- [Azure OpenAI](/providers/ai-sdk-providers/azure)
- [Anthropic](/providers/ai-sdk-providers/anthropic)
- [Open Responses](/providers/ai-sdk-providers/open-responses)
- [Claude Platform on AWS](/providers/ai-sdk-providers/anthropic-aws)
- [Amazon Bedrock](/providers/ai-sdk-providers/amazon-bedrock)
- [Groq](/providers/ai-sdk-providers/groq)
- [Fal](/providers/ai-sdk-providers/fal)
- [AssemblyAI](/providers/ai-sdk-providers/assemblyai)
- [GMI Cloud](/providers/ai-sdk-providers/gmicloud)
- [DeepInfra](/providers/ai-sdk-providers/deepinfra)
- [Deepgram](/providers/ai-sdk-providers/deepgram)
- [Black Forest Labs](/providers/ai-sdk-providers/black-forest-labs)
- [Gladia](/providers/ai-sdk-providers/gladia)
- [Google](/providers/ai-sdk-providers/google)
- [Hume](/providers/ai-sdk-providers/hume)
- [Google Vertex AI](/providers/ai-sdk-providers/google-vertex)
- [Rev.ai](/providers/ai-sdk-providers/revai)
- [Baseten](/providers/ai-sdk-providers/baseten)
- [Hugging Face](/providers/ai-sdk-providers/huggingface)
- [QuiverAI](/providers/ai-sdk-providers/quiverai)
- [Fish Audio](/providers/ai-sdk-providers/fish-audio)
- [Mistral AI](/providers/ai-sdk-providers/mistral)
- [Z.AI](/providers/ai-sdk-providers/zai)
- [Together.ai](/providers/ai-sdk-providers/togetherai)
- [Cohere](/providers/ai-sdk-providers/cohere)
- [Fireworks](/providers/ai-sdk-providers/fireworks)
- [Voyage AI](/providers/ai-sdk-providers/voyage)
- [DeepSeek](/providers/ai-sdk-providers/deepseek)
- [Moonshot AI](/providers/ai-sdk-providers/moonshotai)
- [Alibaba](/providers/ai-sdk-providers/alibaba)
- [MiniMax](/providers/ai-sdk-providers/minimax)
- [Cerebras](/providers/ai-sdk-providers/cerebras)
- [Replicate](/providers/ai-sdk-providers/replicate)
- [Prodia](/providers/ai-sdk-providers/prodia)
- [Perplexity](/providers/ai-sdk-providers/perplexity)
- [Luma](/providers/ai-sdk-providers/luma)
- [ByteDance](/providers/ai-sdk-providers/bytedance)
- [Kling AI](/providers/ai-sdk-providers/klingai)
- [ElevenLabs](/providers/ai-sdk-providers/elevenlabs)
- [Cartesia](/providers/ai-sdk-providers/cartesia)


[Full Sitemap](/sitemap.md)