# Amazon Transcribe (/en/ai/platform/models/asr/amazon)

> For AI agents: see the complete documentation index at [llms.txt](/llms.txt).

> Documentation: Conversational AI.
> Documentation version: Preview.
> This document describes only this version. [Version index](/llms/doc-versions-convoai-guides-v2.txt).


Amazon provides advanced automatic speech recognition with high accuracy and support for multiple languages, designed for real-time conversational AI applications.

## Sample configuration

The following example shows how to configure Amazon Transcribe as the agent's ASR when you create or update an agent. For a complete example, see [Create an agent and start a session](/en/ai/platform/get-started/start-stop-agent#create-an-agent).

Amazon Transcribe supports BYOK only. It isn't available in managed mode. Store your AWS credentials in a secret set, and refer to them from the agent. For details, see [Use your own provider keys](/en/ai/platform/build/use-your-own-keys).

**Python SDK**

```python
from agora_agent import Agent, AmazonSTT, secret_ref

# client is your configured Agora client
agent = (
    Agent(client=client)
    .with_stt(
        AmazonSTT(
            access_key=secret_ref("support_prod", "amazon_access_key_id"),
            secret_key=secret_ref("support_prod", "amazon"),
            region="<AWS_ASR_REGION>",
            language="en-US",
            additional_params={"media_sample_rate_hz": 16000, "media_encoding": "pcm"},
        )
    )
    .with_llm(...)  # configure your LLM vendor
    .with_tts(...)  # configure your TTS vendor
)
```

**TypeScript SDK**

```ts
import { Agent, AmazonSTT, secretRef } from 'agora-agents';

// client is your configured Agora client
const agent = new Agent({ client })
  .withStt(
    new AmazonSTT({
      accessKey: secretRef('support_prod', 'amazon_access_key_id'),
      secretKey: secretRef('support_prod', 'amazon'),
      region: '<AWS_ASR_REGION>',
      language: 'en-US',
      additionalParams: { media_sample_rate_hz: 16000, media_encoding: 'pcm' },
    }),
  )
  .withLlm(/* configure your LLM vendor */)
  .withTts(/* configure your TTS vendor */);
```

**Go SDK**

```go
// client is your configured Agora client
agent := agentkit.NewAgent(client).
	WithStt(vendors.NewAmazonSTT(vendors.AmazonSTTOptions{
		AccessKey: agentkit.SecretRef("support_prod", "amazon_access_key_id"),
		SecretKey: agentkit.SecretRef("support_prod", "amazon"),
		Region:    "<AWS_ASR_REGION>",
		Language:  "en-US",
		AdditionalParams: map[string]interface{}{
			"media_sample_rate_hz": 16000,
			"media_encoding":       "pcm",
		},
	})).
	WithLlm( /* configure your LLM vendor */ ).
	WithTts( /* configure your TTS vendor */ )
```

**REST API**

Set `credential.mode` to `byok`, and set `credential.fields.access_key_id` and `credential.fields.secret_access_key` to references to your AWS access key ID and secret access key in a secret set. In the following example, they're stored as `amazon_access_key_id` and `amazon` in the `support_prod` set:

```json
"asr": {
  "credential": {
    "mode": "byok",
    "fields": {
      "access_key_id": "$secrets.support_prod.amazon_access_key_id",
      "secret_access_key": "$secrets.support_prod.amazon"
    }
  },
  "vendor": "amazon",
  "language": "en-US",
  "params": {
    "language_code": "en-US",
    "region": "<AWS_ASR_REGION>",
    "media_sample_rate_hz": 16000,
    "media_encoding": "pcm"
  }
}
```

## Key parameters

The `asr` block takes the following fields. In the SDKs, `AmazonSTT` sets them from its options, and passes any other Amazon Transcribe parameters from its additional parameters option to `params`.

**asr required**

**`vendor` (string) required**

Set to `amazon`.

**`credential` (object) required**

How the agent authenticates with Amazon Transcribe. Set `mode` to `byok`, and set `fields.access_key_id` and `fields.secret_access_key` to `$secrets.<set>.<key>` references to your AWS access key ID and secret access key. Get both from the [AWS IAM Console](https://console.aws.amazon.com/iam/).

**`language` (string) required**

The language code for speech recognition, for example, `en-US`, `es-US`, or `fr-FR`. See [supported languages](https://docs.aws.amazon.com/transcribe/latest/dg/supported-languages.html) for available language codes.

**`params` (object) required**

**`region` (string) required**

The AWS region where the Transcribe service is hosted, for example, `us-east-1`, `us-west-2`, or `eu-west-1`. See [AWS regions](https://docs.aws.amazon.com/general/latest/gr/transcribe.html) for available regions.

**`language_code` (string) required**

The language code for Amazon Transcribe. Use the same value as `language`.

**`media_sample_rate_hz` (integer) optional**

The sample rate in Hertz for the audio input, for example, `16000` or `8000`.

**`media_encoding` (string) optional**

The encoding format of the audio input, for example, `pcm`, `opus`, or `flac`.

> **Caution**
>
> The parameters listed on this page are validated for use with the Conversational AI Platform. Required parameters must be provided as documented. Any additional parameters in `params` are passed through directly to Amazon Transcribe without validation. For a full list of supported options, refer to the [Amazon official documentation](https://docs.aws.amazon.com/transcribe/latest/dg/streaming.html).

This integration is fully supported for use with the Conversational AI Platform. While it has completed functional validation, it is newer to the platform, and additional provider-specific edge cases may be identified as usage scales across a broader range of applications and workloads.