# Identifying the dominant languages in your media Amazon Transcribe is able to automatically identify the languages spoken in your media without you having to specify a language code. [Batch language identification](lang-id-batch.md) can identify the dominant language spoken in your media file or, if your media contains multiple languages, it can identify all languages spoken. To improve language identification accuracy, you can optionally provide a list of two or more languages you think may be present in your media. [Streaming language identification](lang-id-stream.md) can identify one language per channel (a maximum of two channels are supported) or, if your stream contains multiple languages, it can identify all languages spoken. Streaming requests must have a minimum of two additional language options included in your request. Providing language options allows for faster language identification. The faster Amazon Transcribe is able to identify the language, the less change there is of data loss in the first few seconds of your stream. **Important** Batch and streaming transcriptions support different languages. Refer to the **Data input** column in the [supported languages table](supported-languages.md) for details. Note that Swedish and Vietnamese are not currently supported with language identification. To learn about monitoring and events with language identification, refer to [Language identification events](monitoring-events.md#lang-id-event). # Language identification with batch transcription jobs Use batch language identification to automatically identify the language, or languages, in your media file. If your media contains only one language, you can enable [single-language identification](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartTranscriptionJob.html#transcribe-StartTranscriptionJob-request-IdentifyLanguage), which identifies the dominant language spoken in your media file and creates your transcript using only this language. If your media contains more than one language, you can enable [multi-language identification](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartTranscriptionJob.html#transcribe-StartTranscriptionJob-request-IdentifyMultipleLanguages), which identifies all languages spoken in your media file and creates your transcript using each identified language. Note that a multi-lingual transcript is produced. You can use other services, such as Amazon Translate, to translate your transcript. Refer to the [supported languages](supported-languages.md) table for a complete list of supported languages and associated language codes. For best results, ensure that your media file contains at least 30 seconds of speech. For usage examples with the AWS Management Console, AWS CLI, and AWS Python SDK, see [Using language identification with batch transcriptions](#lang-id-batch-examples). ## Identifying languages in multi-language audio Multi-language identification is intended for multi-lingual media files, and provides you with a transcript that reflects all [supported languages](supported-languages.md) spoken in your media. This means that if speakers change languages mid-conversation, or if each participant is speaking a different language, your transcription output detects and transcribes each language correctly. For example, if your media contains a bilingual speaker who is alternating between US English (`en-US`) and Hindi (`hi-IN`), multi-language identification can identify and transcribe spoken US English as `en-US` and spoken Hindi as `hi-IN`. This differs from single-language identification, where only one dominant language is used to create a transcript. In this case, any spoken language that is not the dominant language is transcribed incorrectly. **Note** Redaction and custom language models are not currently supported with multi-language identification. **Note** The following languages are currently supported with multi-language identification: en-AB, en-AU, en-GB, en-IE, en-IN, en-NZ, en-US, en-WL, en-ZA, es-ES, es-US, fr-CA, fr-FR, zh-CN, zh-TW, pt-BR, pt-PT, de-CH, de-DE, af-ZA, ar-AE, da-DK, he-IL, hi-IN, id-ID, fa-IR, it-IT, ja-JP, ko-KR, ms-MY, nl-NL, ru-RU, ta-IN, te-IN, th-TH, tr-TR Multi-language transcripts provide a summary of detected languages and the total time that each language is spoken in your media. Here's an example: ``` "results": { "transcripts": [ { "transcript": "welcome to Amazon transcribe. ये तो उदाहरण हैं क्या कैसे कर सकते हैं ।一つのファイルに複数の言語を書き写す" } ], ... "language_codes": [ { "language_code": "en-US", "duration_in_seconds": 2.45 }, { "language_code": "hi-IN", "duration_in_seconds": 5.325 }, { "language_code": "ja-JP", "duration_in_seconds": 4.15 } ] } ``` ## Improving language identification accuracy With language identification, you have the option to include a list of languages you think may be present in your media. Including language options (`LanguageOptions`) restricts Amazon Transcribe to using only the languages that you specify when matching your audio to the correct language, which can speed up language identification and improve the accuracy associated with assigning the correct language dialect. If you choose to include language codes, you must include at least two. There's no limit on the number of language codes you can include, but we recommend using between two and five for optimal efficiency and accuracy. **Note** If you include language codes with your request and none of the language codes you provide match the language, or languages, identified in your audio, Amazon Transcribe selects the closest language match from your specified language codes. It then produces a transcript in that language. For example, if your media is in US English (`en-US`) and you provide Amazon Transcribe with the language codes `zh-CN`, `fr-FR`, and `de-DE`, Amazon Transcribe is likely to match your media to German (`de-DE`) and produce a German-language transcription. Mismatching language codes and spoken languages can result in an inaccurate transcript, so we recommend caution when including language codes. ## Combining language identification with other Amazon Transcribe features You can use batch language identification in combination with any other Amazon Transcribe feature. If combining language identification with other features, you are limited to the languages supported with those features. For example, if using language identification with content redaction, you are limited to US English (`en-US`) or US Spanish (`es-US`), as this is only language available for redaction. Refer to [Supported languages and language-specific features](supported-languages.md) for more information. **Important** If you're using automatic language identification with content redaction enabled and your audio contains languages other than US English (`en-US`) or US Spanish (`es-US`), only the US English or US Spanish content is redacted in your transcript. Other languages cannot be redacted and there are no warnings or job failures. **Custom language models, custom vocabularies, and custom vocabulary filters** If you want to add one or more custom language models, custom vocabularies, or custom vocabulary filters to your language identification request, you must include the [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_LanguageIdSettings.html](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_LanguageIdSettings.html) parameter. You can then specify a language code with a corresponding custom language model, custom vocabulary, and custom vocabulary filter. Note that multi-language identification doesn't support custom language models. It's recommended that you include `LanguageOptions` when using [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_LanguageIdSettings.html](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_LanguageIdSettings.html) to ensure that the correct language dialect is identified. For example, if you specify an `en-US` custom vocabulary, but Amazon Transcribe determines that the language spoken in your media is `en-AU`, your custom vocabulary *is not* applied to your transcription. If you include `LanguageOptions` and specify `en-US` as the only English language dialect, your custom vocabulary *is* applied to your transcription. For examples of [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_LanguageIdSettings.html](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_LanguageIdSettings.html) in a request, refer to Option 2 in the **AWS CLI** and **AWS SDKs** dropdown panels in the [Using language identification with batch transcriptions](#lang-id-batch-examples) section. ## Using language identification with batch transcriptions You can use automatic language identification in a batch transcription job using the **AWS Management Console**, **AWS CLI**, or **AWS SDKs**; see the following for examples: ### AWS Management Console 1. Sign in to the [AWS Management Console](https://console.aws.amazon.com/transcribe/). 1. In the navigation pane, choose **Transcription jobs**, then select **Create job** (top right). This opens the **Specify job details** page. 1. In the **Job settings** panel, find the **Language settings** section and select **Automatic language identification** or **Automatic multiple languages identification**. You have the option to select multiple language options (from the *Select languages* dropdown box) if you know which languages are present in your audio file. Providing language options can improve accuracy, but is not required. ![\[Amazon Transcribe console screenshot: the 'job settings' pane on the 'specify job details' page.\]](http://docs.aws.amazon.com/transcribe/latest/dg/images/lang-id-batch1.png) 1. Fill in any other fields you want to include on the **Specify job details** page, then select **Next**. This takes you to the **Configure job - *optional*** page. ![\[Amazon Transcribe console screenshot: the 'configure job' page.\]](http://docs.aws.amazon.com/transcribe/latest/dg/images/lang-id-configure-batch.png) 1. Select **Create job** to run your transcription job. ### AWS CLI This example uses the [start-transcription-job](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/transcribe/start-transcription-job.html) command and `IdentifyLanguage` parameter. For more information, see [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartTranscriptionJob.html](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartTranscriptionJob.html) and [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_LanguageIdSettings.html](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_LanguageIdSettings.html). **Option 1**: Without the `language-id-settings` parameter. Use this option if you are **not** including a custom language model, custom vocabulary, or custom vocabulary filter in your request. `language-options` is optional, but recommended. ``` aws transcribe start-transcription-job \ --region us-west-2 \ --transcription-job-name my-first-transcription-job \ --media MediaFileUri=s3://amzn-s3-demo-bucket/my-input-files/my-media-file.flac \ --output-bucket-name amzn-s3-demo-bucket \ --output-key my-output-files/ \ --identify-language \ (or --identify-multiple-languages) \ --language-options "en-US" "hi-IN" ``` **Option 2**: With the `language-id-settings` parameter. Use this option if you **are** including a custom language model, custom vocabulary, or custom vocabulary filter in your request. ``` aws transcribe start-transcription-job \ --region us-west-2 \ --transcription-job-name my-first-transcription-job \ --media MediaFileUri=s3://amzn-s3-demo-bucket/my-input-files/my-media-file.flac \ --output-bucket-name amzn-s3-demo-bucket \ --output-key my-output-files/ \ --identify-language \ (or --identify-multiple-languages) --language-options "en-US" "hi-IN" \ --language-id-settings en-US=VocabularyName=my-en-US-vocabulary,en-US=VocabularyFilterName=my-en-US-vocabulary-filter,en-US=LanguageModelName=my-en-US-language-model,hi-IN=VocabularyName=my-hi-IN-vocabulary,hi-IN=VocabularyFilterName=my-hi-IN-vocabulary-filter ``` Here's another example using the [start-transcription-job](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/transcribe/start-transcription-job.html) command, and a request body that identifies the language. ``` aws transcribe start-transcription-job \ --region us-west-2 \ --cli-input-json file://filepath/my-first-language-id-job.json ``` The file *my-first-language-id-job.json* contains the following request body. **Option 1**: Without the `LanguageIdSettings` parameter. Use this option if you are **not** including a custom language model, custom vocabulary, or custom vocabulary filter in your request. `LanguageOptions` is optional, but recommended. ``` { "TranscriptionJobName": "my-first-transcription-job", "Media": { "MediaFileUri": "s3://amzn-s3-demo-bucket/my-input-files/my-media-file.flac" }, "OutputBucketName": "amzn-s3-demo-bucket", "OutputKey": "my-output-files/", "IdentifyLanguage": true, (or "IdentifyMultipleLanguages": true), "LanguageOptions": [ "en-US", "hi-IN" ] } ``` **Option 2**: With the `LanguageIdSettings` parameter. Use this option if you **are** including a custom language model, custom vocabulary, or custom vocabulary filter in your request. ``` { "TranscriptionJobName": "my-first-transcription-job", "Media": { "MediaFileUri": "s3://amzn-s3-demo-bucket/my-input-files/my-media-file.flac" }, "OutputBucketName": "amzn-s3-demo-bucket", "OutputKey": "my-output-files/", "IdentifyLanguage": true, (or "IdentifyMultipleLanguages": true) "LanguageOptions": [ "en-US", "hi-IN" ], "LanguageIdSettings": { "en-US" : { "LanguageModelName": "my-en-US-language-model", "VocabularyFilterName": "my-en-US-vocabulary-filter", "VocabularyName": "my-en-US-vocabulary" }, "hi-IN": { "VocabularyName": "my-hi-IN-vocabulary", "VocabularyFilterName": "my-hi-IN-vocabulary-filter" } } } ``` ### AWS SDK for Python (Boto3) This example uses the AWS SDK for Python (Boto3) to identify your file's language using the `IdentifyLanguage` argument for the [start\$1transcription\$1job](https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/transcribe.html#TranscribeService.Client.start_transcription_job) method. For more information, see [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartTranscriptionJob.html](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartTranscriptionJob.html) and [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_LanguageIdSettings.html](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_LanguageIdSettings.html). For additional examples using the AWS SDKs, including feature-specific, scenario, and cross-service examples, refer to the [Code examples for Amazon Transcribe using AWS SDKs](service_code_examples.md) chapter. **Option 1**: Without the `LanguageIdSettings` parameter. Use this option if you are **not** including a custom language model, custom vocabulary, or custom vocabulary filter in your request. `LanguageOptions` is optional, but recommended. ``` from __future__ import print_function import time import boto3 transcribe = boto3.client('transcribe', 'us-west-2') job_name = "my-first-transcription-job" job_uri = "s3://amzn-s3-demo-bucket/my-input-files/my-media-file.flac" transcribe.start_transcription_job( TranscriptionJobName = job_name, Media = { 'MediaFileUri': job_uri }, OutputBucketName = 'amzn-s3-demo-bucket', OutputKey = 'my-output-files/', MediaFormat = 'flac', IdentifyLanguage = True, (or IdentifyMultipleLanguages = True), LanguageOptions = [ 'en-US', 'hi-IN' ] ) while True: status = transcribe.get_transcription_job(TranscriptionJobName = job_name) if status['TranscriptionJob']['TranscriptionJobStatus'] in ['COMPLETED', 'FAILED']: break print("Not ready yet...") time.sleep(5) print(status) ``` **Option 2**: With the `LanguageIdSettings` parameter. Use this option if you **are** including a custom language model, custom vocabulary, or custom vocabulary filter in your request. ``` from __future__ import print_function import time import boto3 transcribe = boto3.client('transcribe') job_name = "my-first-transcription-job" job_uri = "s3://amzn-s3-demo-bucket/my-input-files/my-media-file.flac" transcribe.start_transcription_job( TranscriptionJobName = job_name, Media = { 'MediaFileUri': job_uri }, OutputBucketName = 'amzn-s3-demo-bucket', OutputKey = 'my-output-files/', MediaFormat='flac', IdentifyLanguage=True, (or IdentifyMultipleLanguages=True) LanguageOptions = [ 'en-US', 'hi-IN' ], LanguageIdSettings={ 'en-US': { 'VocabularyName': 'my-en-US-vocabulary', 'VocabularyFilterName': 'my-en-US-vocabulary-filter', 'LanguageModelName': 'my-en-US-language-model' }, 'hi-IN': { 'VocabularyName': 'my-hi-IN-vocabulary', 'VocabularyFilterName': 'my-hi-IN-vocabulary-filter' } } ) while True: status = transcribe.get_transcription_job(TranscriptionJobName = job_name) if status['TranscriptionJob']['TranscriptionJobStatus'] in ['COMPLETED', 'FAILED']: break print("Not ready yet...") time.sleep(5) print(status) ``` # Language identification with streaming transcriptions Streaming language identification can identify the dominant language spoken in your media stream. Amazon Transcribe requires a minimum of one second of speech to identify the language. If your stream contains only one language, you can enable single-language identification, which identifies the dominant language spoken in your media file and creates your transcript using only this language. If your stream contains more than one language, you can enable multi-language identification, which identifies all languages spoken in your stream and creates your transcript using each identified language. Note that a multi-lingual transcript is produced. You can use other services, such as Amazon Transcribe, to translate your transcript. To use streaming language identification, you must provide at least two language codes, and you can select only one language dialect per language per stream. This means that you cannot select `en-US` and `en-AU` as language options for the same transcription. You also have the option to select a preferred language from the set of language codes you provide. Adding a preferred language can speed up the language identification process, which is helpful for short audio clips. **Important** If none of the language codes you provide match the language, or languages, identified in your audio, Amazon Transcribe selects the closest language match from your specified language codes. It then produces a transcript in that language. For example, if your media is in US English (`en-US`) and you provide Amazon Transcribe with the language codes `zh-CN`, `fr-FR`, and `de-DE`, Amazon Transcribe is likely to match your media to German (`de-DE`) and produce a German-language transcription. Mismatching language codes and spoken languages can result in an inaccurate transcript, so we recommend caution when including language codes. If your media contains two channels, Amazon Transcribe can identify the dominant language spoken in each channel. In this case, set the [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_Settings.html#transcribe-Type-Settings-ChannelIdentification](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_Settings.html#transcribe-Type-Settings-ChannelIdentification) parameter to `true` and each channel is transcribed separately. Note that the default for this parameter is `false`. If you don't change it, only the first channel is transcribed and only one language is identified. Streaming language identification can't be combined with custom language models or redaction. If combining language identification with other features, you are limited to the languages supported with those features, and also with streaming transcriptions. Refer to [Supported languages](supported-languages.md). **Note** PCM and FLAC are the only supported audio formats for streaming language identification. For multi-language identification, only PCM is supported. ## Identifying languages in multi-language audio Multi-language identification is intended for multi-lingual streams, and provides you with a transcript that reflects all supported languages spoken in your stream. This means that if speakers change languages mid-conversation, or if each participant is speaking a different language, your transcription output detects and transcribes each language correctly. For example, if your stream contains a bilingual speaker who is alternating between US English (`en-US`) and Hindi (`hi-IN`), multi-language identification can identify and transcribe spoken US English as `en-US` and spoken Hindi as `hi-IN`. This differs from single-language identification, where only one dominant language is used to create a transcript. In this case, any spoken language that is not the dominant language is transcribed incorrectly. **Note** Redaction and custom language models are not currently supported with multi-language identification. ## Using language identification with streaming media You can use automatic language identification in a streaming transcription using the **AWS Management Console**, **HTTP/2**, or **WebSockets**; see the following for examples: ### AWS Management Console 1. Sign in to the [AWS Management Console](https://console.aws.amazon.com/transcribe/). 1. In the navigation pane, choose **Real-time transcription**. Scroll down to **Language settings** and expand this field if it is minimized. ![\[Amazon Transcribe console screenshot: the collapsed 'language settings' tab on the 'real-time transcription' page.\]](http://docs.aws.amazon.com/transcribe/latest/dg/images/lang-id-stream1.png) 1. Select **Automatic language identification** or **Automatic multiple languages identification**. ![\[Amazon Transcribe console screenshot: the expanded 'language settings' tab.\]](http://docs.aws.amazon.com/transcribe/latest/dg/images/lang-id-stream2.png) 1. Provide a minimum of two language codes for your transcription. Note that you can provide only one dialect per language. For example, you cannot select both `en-US` and `en-GB` as language options for the same transcription. ![\[Amazon Transcribe console screenshot: the language code selection dropdown menu.\]](http://docs.aws.amazon.com/transcribe/latest/dg/images/lang-id-stream3.png) 1. (Optional) From the subset of languages you selected in the previous step, you can choose a preferred language for your transcript. ![\[Amazon Transcribe console screenshot: the 'language settings' panel with preferred language options.\]](http://docs.aws.amazon.com/transcribe/latest/dg/images/lang-id-stream4.png) 1. You're now ready to transcribe your stream. Select **Start streaming** and begin speaking. To end your dictation, select **Stop streaming**. ### HTTP/2 stream This example creates an HTTP/2 request with language identification enabled. For more information on using HTTP/2 streaming with Amazon Transcribe, see [Setting up an HTTP/2 stream](streaming-setting-up.md#streaming-http2). For more detail on parameters and headers specific to Amazon Transcribe, see [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_streaming_StartStreamTranscription.html](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_streaming_StartStreamTranscription.html). ``` POST /stream-transcription HTTP/2 host: transcribestreaming.us-west-2.amazonaws.com X-Amz-Target: com.amazonaws.transcribe.Transcribe.StartStreamTranscription Content-Type: application/vnd.amazon.eventstream X-Amz-Content-Sha256: string X-Amz-Date: 20220208T235959Z Authorization: AWS4-HMAC-SHA256 Credential=access-key/20220208/us-west-2/transcribe/aws4_request, SignedHeaders=content-type;host;x-amz-content-sha256;x-amz-date;x-amz-target;x-amz-security-token, Signature=string x-amzn-transcribe-media-encoding: flac x-amzn-transcribe-sample-rate: 16000 x-amzn-transcribe-identify-language: true x-amzn-transcribe-language-options: en-US,de-DE x-amzn-transcribe-preferred-language: en-US transfer-encoding: chunked ``` This example creates an HTTP/2 request with multiple languages identification enabled. For more information on using HTTP/2 streaming with Amazon Transcribe, see [Setting up an HTTP/2 stream](streaming-setting-up.md#streaming-http2). For more detail on parameters and headers specific to Amazon Transcribe, see [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_streaming_StartStreamTranscription.html](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_streaming_StartStreamTranscription.html). ``` POST /stream-transcription HTTP/2 host: transcribestreaming.us-west-2.amazonaws.com X-Amz-Target: com.amazonaws.transcribe.Transcribe.StartStreamTranscription Content-Type: application/vnd.amazon.eventstream X-Amz-Content-Sha256: string X-Amz-Date: 20220208T235959Z Authorization: AWS4-HMAC-SHA256 Credential=access-key/20220208/us-west-2/transcribe/aws4_request, SignedHeaders=content-type;host;x-amz-content-sha256;x-amz-date;x-amz-target;x-amz-security-token, Signature=string x-amzn-transcribe-media-encoding: flac x-amzn-transcribe-sample-rate: 16000 x-amzn-transcribe-identify-multiple-languages: true x-amzn-transcribe-language-options: en-US,de-DE x-amzn-transcribe-preferred-language: en-US transfer-encoding: chunked ``` If you use `identify-language` or `identify-multiple-languages` in your request, you must also include `language-options`. You cannot use both `language-code` and `identify-language` in the same request. Parameter definitions can be found in the [API Reference](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_Reference.html); parameters common to all AWS API operations are listed in the [Common Parameters](https://docs.aws.amazon.com/transcribe/latest/APIReference/CommonParameters.html) section. ### WebSocket stream This example creates a presigned URL that uses language identification in a WebSocket stream. Line breaks have been added for readability. For more information on using WebSocket streams with Amazon Transcribe, see [Setting up a WebSocket stream](streaming-setting-up.md#streaming-websocket). For more detail on parameters, see [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_streaming_StartStreamTranscription.html](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_streaming_StartStreamTranscription.html). ``` GET wss://transcribestreaming.us-west-2.amazonaws.com:8443/stream-transcription-websocket? &X-Amz-Algorithm=AWS4-HMAC-SHA256 &X-Amz-Credential=AKIAIOSFODNN7EXAMPLE%2F20220208%2Fus-west-2%2Ftranscribe%2Faws4_request &X-Amz-Date=20220208T235959Z &X-Amz-Expires=300 &X-Amz-Security-Token=security-token &X-Amz-Signature=string &X-Amz-SignedHeaders=content-type%3Bhost%3Bx-amz-date &media-encoding=flac &sample-rate=16000 &identify-language=true &language-options=en-US,de-DE &preferred-language=en-US ``` This example creates a presigned URL that uses multiple languages identification in a WebSocket stream. Line breaks have been added for readability. For more information on using WebSocket streams with Amazon Transcribe, see [Setting up a WebSocket stream](streaming-setting-up.md#streaming-websocket). For more detail on parameters, see [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_streaming_StartStreamTranscription.html](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_streaming_StartStreamTranscription.html). ``` GET wss://transcribestreaming.us-west-2.amazonaws.com:8443/stream-transcription-websocket? &X-Amz-Algorithm=AWS4-HMAC-SHA256 &X-Amz-Credential=AKIAIOSFODNN7EXAMPLE%2F20220208%2Fus-west-2%2Ftranscribe%2Faws4_request &X-Amz-Date=20220208T235959Z &X-Amz-Expires=300 &X-Amz-Security-Token=security-token &X-Amz-Signature=string &X-Amz-SignedHeaders=content-type%3Bhost%3Bx-amz-date &media-encoding=flac &sample-rate=16000 &identify-multiple-languages=true &language-options=en-US,de-DE &preferred-language=en-US ``` If you use `identify-language` or `identify-multiple-languages` in your request, you must also include `language-options`. You cannot use both `language-code` and `identify-language` in the same request. Parameter definitions can be found in the [API Reference](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_Reference.html); parameters common to all AWS API operations are listed in the [Common Parameters](https://docs.aws.amazon.com/transcribe/latest/APIReference/CommonParameters.html) section.