StartStreamTranscriptionCommand

Starts a bidirectional HTTP/2 or WebSocket stream where audio is streamed to Amazon Transcribe and the transcription results are streamed to your application.

The following parameters are required:

  • language-code or identify-language or identify-multiple-language

  • media-encoding

  • sample-rate

For more information on streaming with Amazon Transcribe, see Transcribing streaming audio .

Example Syntax

Use a bare-bones client and the command you need to make an API call.

import { TranscribeStreamingClient, StartStreamTranscriptionCommand } from "@aws-sdk/client-transcribe-streaming"; // ES Modules import
// const { TranscribeStreamingClient, StartStreamTranscriptionCommand } = require("@aws-sdk/client-transcribe-streaming"); // CommonJS import
const client = new TranscribeStreamingClient(config);
const input = { // StartStreamTranscriptionRequest
  LanguageCode: "en-US" || "en-GB" || "es-US" || "fr-CA" || "fr-FR" || "en-AU" || "it-IT" || "de-DE" || "pt-BR" || "ja-JP" || "ko-KR" || "zh-CN" || "th-TH" || "es-ES" || "ar-SA" || "pt-PT" || "ca-ES" || "ar-AE" || "hi-IN" || "zh-HK" || "nl-NL" || "no-NO" || "sv-SE" || "pl-PL" || "fi-FI" || "zh-TW" || "en-IN" || "en-IE" || "en-NZ" || "en-AB" || "en-ZA" || "en-WL" || "de-CH" || "af-ZA" || "eu-ES" || "hr-HR" || "cs-CZ" || "da-DK" || "fa-IR" || "gl-ES" || "el-GR" || "he-IL" || "id-ID" || "lv-LV" || "ms-MY" || "ro-RO" || "ru-RU" || "sr-RS" || "sk-SK" || "so-SO" || "tl-PH" || "uk-UA" || "vi-VN" || "zu-ZA",
  MediaSampleRateHertz: Number("int"), // required
  MediaEncoding: "pcm" || "ogg-opus" || "flac", // required
  VocabularyName: "STRING_VALUE",
  SessionId: "STRING_VALUE",
  AudioStream: { // AudioStream Union: only one key present
    AudioEvent: { // AudioEvent
      AudioChunk: new Uint8Array(), // e.g. Buffer.from("") or new TextEncoder().encode("")
    },
    ConfigurationEvent: { // ConfigurationEvent
      ChannelDefinitions: [ // ChannelDefinitions
        { // ChannelDefinition
          ChannelId: Number("int"), // required
          ParticipantRole: "AGENT" || "CUSTOMER", // required
        },
      ],
      PostCallAnalyticsSettings: { // PostCallAnalyticsSettings
        OutputLocation: "STRING_VALUE", // required
        DataAccessRoleArn: "STRING_VALUE", // required
        ContentRedactionOutput: "redacted" || "redacted_and_unredacted",
        OutputEncryptionKMSKeyId: "STRING_VALUE",
      },
    },
  },
  VocabularyFilterName: "STRING_VALUE",
  VocabularyFilterMethod: "remove" || "mask" || "tag",
  ShowSpeakerLabel: true || false,
  EnableChannelIdentification: true || false,
  NumberOfChannels: Number("int"),
  EnablePartialResultsStabilization: true || false,
  PartialResultsStability: "high" || "medium" || "low",
  ContentIdentificationType: "PII",
  ContentRedactionType: "PII",
  PiiEntityTypes: "STRING_VALUE",
  LanguageModelName: "STRING_VALUE",
  IdentifyLanguage: true || false,
  LanguageOptions: "STRING_VALUE",
  PreferredLanguage: "en-US" || "en-GB" || "es-US" || "fr-CA" || "fr-FR" || "en-AU" || "it-IT" || "de-DE" || "pt-BR" || "ja-JP" || "ko-KR" || "zh-CN" || "th-TH" || "es-ES" || "ar-SA" || "pt-PT" || "ca-ES" || "ar-AE" || "hi-IN" || "zh-HK" || "nl-NL" || "no-NO" || "sv-SE" || "pl-PL" || "fi-FI" || "zh-TW" || "en-IN" || "en-IE" || "en-NZ" || "en-AB" || "en-ZA" || "en-WL" || "de-CH" || "af-ZA" || "eu-ES" || "hr-HR" || "cs-CZ" || "da-DK" || "fa-IR" || "gl-ES" || "el-GR" || "he-IL" || "id-ID" || "lv-LV" || "ms-MY" || "ro-RO" || "ru-RU" || "sr-RS" || "sk-SK" || "so-SO" || "tl-PH" || "uk-UA" || "vi-VN" || "zu-ZA",
  IdentifyMultipleLanguages: true || false,
  VocabularyNames: "STRING_VALUE",
  VocabularyFilterNames: "STRING_VALUE",
};
const command = new StartStreamTranscriptionCommand(input);
const response = await client.send(command);
// { // StartStreamTranscriptionResponse
//   RequestId: "STRING_VALUE",
//   LanguageCode: "en-US" || "en-GB" || "es-US" || "fr-CA" || "fr-FR" || "en-AU" || "it-IT" || "de-DE" || "pt-BR" || "ja-JP" || "ko-KR" || "zh-CN" || "th-TH" || "es-ES" || "ar-SA" || "pt-PT" || "ca-ES" || "ar-AE" || "hi-IN" || "zh-HK" || "nl-NL" || "no-NO" || "sv-SE" || "pl-PL" || "fi-FI" || "zh-TW" || "en-IN" || "en-IE" || "en-NZ" || "en-AB" || "en-ZA" || "en-WL" || "de-CH" || "af-ZA" || "eu-ES" || "hr-HR" || "cs-CZ" || "da-DK" || "fa-IR" || "gl-ES" || "el-GR" || "he-IL" || "id-ID" || "lv-LV" || "ms-MY" || "ro-RO" || "ru-RU" || "sr-RS" || "sk-SK" || "so-SO" || "tl-PH" || "uk-UA" || "vi-VN" || "zu-ZA",
//   MediaSampleRateHertz: Number("int"),
//   MediaEncoding: "pcm" || "ogg-opus" || "flac",
//   VocabularyName: "STRING_VALUE",
//   SessionId: "STRING_VALUE",
//   TranscriptResultStream: { // TranscriptResultStream Union: only one key present
//     TranscriptEvent: { // TranscriptEvent
//       Transcript: { // Transcript
//         Results: [ // ResultList
//           { // Result
//             ResultId: "STRING_VALUE",
//             StartTime: Number("double"),
//             EndTime: Number("double"),
//             IsPartial: true || false,
//             Alternatives: [ // AlternativeList
//               { // Alternative
//                 Transcript: "STRING_VALUE",
//                 Items: [ // ItemList
//                   { // Item
//                     StartTime: Number("double"),
//                     EndTime: Number("double"),
//                     Type: "pronunciation" || "punctuation",
//                     Content: "STRING_VALUE",
//                     VocabularyFilterMatch: true || false,
//                     Speaker: "STRING_VALUE",
//                     Confidence: Number("double"),
//                     Stable: true || false,
//                   },
//                 ],
//                 Entities: [ // EntityList
//                   { // Entity
//                     StartTime: Number("double"),
//                     EndTime: Number("double"),
//                     Category: "STRING_VALUE",
//                     Type: "STRING_VALUE",
//                     Content: "STRING_VALUE",
//                     Confidence: Number("double"),
//                   },
//                 ],
//               },
//             ],
//             ChannelId: "STRING_VALUE",
//             LanguageCode: "en-US" || "en-GB" || "es-US" || "fr-CA" || "fr-FR" || "en-AU" || "it-IT" || "de-DE" || "pt-BR" || "ja-JP" || "ko-KR" || "zh-CN" || "th-TH" || "es-ES" || "ar-SA" || "pt-PT" || "ca-ES" || "ar-AE" || "hi-IN" || "zh-HK" || "nl-NL" || "no-NO" || "sv-SE" || "pl-PL" || "fi-FI" || "zh-TW" || "en-IN" || "en-IE" || "en-NZ" || "en-AB" || "en-ZA" || "en-WL" || "de-CH" || "af-ZA" || "eu-ES" || "hr-HR" || "cs-CZ" || "da-DK" || "fa-IR" || "gl-ES" || "el-GR" || "he-IL" || "id-ID" || "lv-LV" || "ms-MY" || "ro-RO" || "ru-RU" || "sr-RS" || "sk-SK" || "so-SO" || "tl-PH" || "uk-UA" || "vi-VN" || "zu-ZA",
//             LanguageIdentification: [ // LanguageIdentification
//               { // LanguageWithScore
//                 LanguageCode: "en-US" || "en-GB" || "es-US" || "fr-CA" || "fr-FR" || "en-AU" || "it-IT" || "de-DE" || "pt-BR" || "ja-JP" || "ko-KR" || "zh-CN" || "th-TH" || "es-ES" || "ar-SA" || "pt-PT" || "ca-ES" || "ar-AE" || "hi-IN" || "zh-HK" || "nl-NL" || "no-NO" || "sv-SE" || "pl-PL" || "fi-FI" || "zh-TW" || "en-IN" || "en-IE" || "en-NZ" || "en-AB" || "en-ZA" || "en-WL" || "de-CH" || "af-ZA" || "eu-ES" || "hr-HR" || "cs-CZ" || "da-DK" || "fa-IR" || "gl-ES" || "el-GR" || "he-IL" || "id-ID" || "lv-LV" || "ms-MY" || "ro-RO" || "ru-RU" || "sr-RS" || "sk-SK" || "so-SO" || "tl-PH" || "uk-UA" || "vi-VN" || "zu-ZA",
//                 Score: Number("double"),
//               },
//             ],
//           },
//         ],
//       },
//     },
//     BadRequestException: { // BadRequestException
//       Message: "STRING_VALUE",
//     },
//     LimitExceededException: { // LimitExceededException
//       Message: "STRING_VALUE",
//     },
//     InternalFailureException: { // InternalFailureException
//       Message: "STRING_VALUE",
//     },
//     ConflictException: { // ConflictException
//       Message: "STRING_VALUE",
//     },
//     ServiceUnavailableException: { // ServiceUnavailableException
//       Message: "STRING_VALUE",
//     },
//   },
//   VocabularyFilterName: "STRING_VALUE",
//   VocabularyFilterMethod: "remove" || "mask" || "tag",
//   ShowSpeakerLabel: true || false,
//   EnableChannelIdentification: true || false,
//   NumberOfChannels: Number("int"),
//   EnablePartialResultsStabilization: true || false,
//   PartialResultsStability: "high" || "medium" || "low",
//   ContentIdentificationType: "PII",
//   ContentRedactionType: "PII",
//   PiiEntityTypes: "STRING_VALUE",
//   LanguageModelName: "STRING_VALUE",
//   IdentifyLanguage: true || false,
//   LanguageOptions: "STRING_VALUE",
//   PreferredLanguage: "en-US" || "en-GB" || "es-US" || "fr-CA" || "fr-FR" || "en-AU" || "it-IT" || "de-DE" || "pt-BR" || "ja-JP" || "ko-KR" || "zh-CN" || "th-TH" || "es-ES" || "ar-SA" || "pt-PT" || "ca-ES" || "ar-AE" || "hi-IN" || "zh-HK" || "nl-NL" || "no-NO" || "sv-SE" || "pl-PL" || "fi-FI" || "zh-TW" || "en-IN" || "en-IE" || "en-NZ" || "en-AB" || "en-ZA" || "en-WL" || "de-CH" || "af-ZA" || "eu-ES" || "hr-HR" || "cs-CZ" || "da-DK" || "fa-IR" || "gl-ES" || "el-GR" || "he-IL" || "id-ID" || "lv-LV" || "ms-MY" || "ro-RO" || "ru-RU" || "sr-RS" || "sk-SK" || "so-SO" || "tl-PH" || "uk-UA" || "vi-VN" || "zu-ZA",
//   IdentifyMultipleLanguages: true || false,
//   VocabularyNames: "STRING_VALUE",
//   VocabularyFilterNames: "STRING_VALUE",
// };

StartStreamTranscriptionCommand Input

Parameter
Type
Description
AudioStream
Required
AsyncIterable<AudioStream> | undefined

An encoded stream of audio blobs. Audio streams are encoded as either HTTP/2 or WebSocket data frames.

For more information, see Transcribing streaming audio .

MediaEncoding
Required
MediaEncoding | undefined

Specify the encoding of your input audio. Supported formats are:

  • FLAC

  • OPUS-encoded audio in an Ogg container

  • PCM (only signed 16-bit little-endian audio formats, which does not include WAV)

For more information, see Media formats .

MediaSampleRateHertz
Required
number | undefined

The sample rate of the input audio (in hertz). Low-quality audio, such as telephone audio, is typically around 8,000 Hz. High-quality audio typically ranges from 16,000 Hz to 48,000 Hz. Note that the sample rate you specify must match that of your audio.

ContentIdentificationType
ContentIdentificationType | undefined

Labels all personally identifiable information (PII) identified in your transcript.

Content identification is performed at the segment level; PII specified in PiiEntityTypes is flagged upon complete transcription of an audio segment. If you don't include PiiEntityTypes in your request, all PII is identified.

You can’t set ContentIdentificationType and ContentRedactionType in the same request. If you set both, your request returns a BadRequestException.

ContentRedactionType
ContentRedactionType | undefined

Redacts all personally identifiable information (PII) identified in your transcript.

Content redaction is performed at the segment level; PII specified in PiiEntityTypes is redacted upon complete transcription of an audio segment. If you don't include PiiEntityTypes in your request, all PII is redacted.

You can’t set ContentRedactionType and ContentIdentificationType in the same request. If you set both, your request returns a BadRequestException.

EnableChannelIdentification
boolean | undefined

Enables channel identification in multi-channel audio.

Channel identification transcribes the audio on each channel independently, then appends the output for each channel into one transcript.

If you have multi-channel audio and do not enable channel identification, your audio is transcribed in a continuous manner and your transcript is not separated by channel.

If you include EnableChannelIdentification in your request, you must also include NumberOfChannels.

For more information, see Transcribing multi-channel audio .

EnablePartialResultsStabilization
boolean | undefined

Enables partial result stabilization for your transcription. Partial result stabilization can reduce latency in your output, but may impact accuracy. For more information, see Partial-result stabilization .

IdentifyLanguage
boolean | undefined

Enables automatic language identification for your transcription.

If you include IdentifyLanguage, you must include a list of language codes, using LanguageOptions, that you think may be present in your audio stream.

You can also include a preferred language using PreferredLanguage. Adding a preferred language can help Amazon Transcribe identify the language faster than if you omit this parameter.

If you have multi-channel audio that contains different languages on each channel, and you've enabled channel identification, automatic language identification identifies the dominant language on each audio channel.

Note that you must include either LanguageCode or IdentifyLanguage or IdentifyMultipleLanguages in your request. If you include more than one of these parameters, your transcription job fails.

Streaming language identification can't be combined with custom language models or redaction.

IdentifyMultipleLanguages
boolean | undefined

Enables automatic multi-language identification in your transcription job request. Use this parameter if your stream contains more than one language. If your stream contains only one language, use IdentifyLanguage instead.

If you include IdentifyMultipleLanguages, you must include a list of language codes, using LanguageOptions, that you think may be present in your stream.

If you want to apply a custom vocabulary or a custom vocabulary filter to your automatic multiple language identification request, include VocabularyNames or VocabularyFilterNames.

Note that you must include one of LanguageCode, IdentifyLanguage, or IdentifyMultipleLanguages in your request. If you include more than one of these parameters, your transcription job fails.

LanguageCode
LanguageCode | undefined

Specify the language code that represents the language spoken in your audio.

If you're unsure of the language spoken in your audio, consider using IdentifyLanguage to enable automatic language identification.

For a list of languages supported with Amazon Transcribe streaming, refer to the Supported languages  table.

LanguageModelName
string | undefined

Specify the name of the custom language model that you want to use when processing your transcription. Note that language model names are case sensitive.

The language of the specified language model must match the language code you specify in your transcription request. If the languages don't match, the custom language model isn't applied. There are no errors or warnings associated with a language mismatch.

For more information, see Custom language models .

LanguageOptions
string | undefined

Specify two or more language codes that represent the languages you think may be present in your media; including more than five is not recommended.

Including language options can improve the accuracy of language identification.

If you include LanguageOptions in your request, you must also include IdentifyLanguage or IdentifyMultipleLanguages.

For a list of languages supported with Amazon Transcribe streaming, refer to the Supported languages  table.

You can only include one language dialect per language per stream. For example, you cannot include en-US and en-AU in the same request.

NumberOfChannels
number | undefined

Specify the number of channels in your audio stream. This value must be 2, as only two channels are supported. If your audio doesn't contain multiple channels, do not include this parameter in your request.

If you include NumberOfChannels in your request, you must also include EnableChannelIdentification.

PartialResultsStability
PartialResultsStability | undefined

Specify the level of stability to use when you enable partial results stabilization (EnablePartialResultsStabilization).

Low stability provides the highest accuracy. High stability transcribes faster, but with slightly lower accuracy.

For more information, see Partial-result stabilization .

PiiEntityTypes
string | undefined

Specify which types of personally identifiable information (PII) you want to redact in your transcript. You can include as many types as you'd like, or you can select ALL.

Values must be comma-separated and can include: ADDRESS, BANK_ACCOUNT_NUMBER, BANK_ROUTING, CREDIT_DEBIT_CVV, CREDIT_DEBIT_EXPIRY, CREDIT_DEBIT_NUMBER, EMAIL, NAME, PHONE, PIN, SSN, or ALL.

Note that if you include PiiEntityTypes in your request, you must also include ContentIdentificationType or ContentRedactionType.

If you include ContentRedactionType or ContentIdentificationType in your request, but do not include PiiEntityTypes, all PII is redacted or identified.

PreferredLanguage
LanguageCode | undefined

Specify a preferred language from the subset of languages codes you specified in LanguageOptions.

You can only use this parameter if you've included IdentifyLanguage and LanguageOptions in your request.

SessionId
string | undefined

Specify a name for your transcription session. If you don't include this parameter in your request, Amazon Transcribe generates an ID and returns it in the response.

ShowSpeakerLabel
boolean | undefined

Enables speaker partitioning (diarization) in your transcription output. Speaker partitioning labels the speech from individual speakers in your media file.

For more information, see Partitioning speakers (diarization) .

VocabularyFilterMethod
VocabularyFilterMethod | undefined

Specify how you want your vocabulary filter applied to your transcript.

To replace words with ***, choose mask.

To delete words, choose remove.

To flag words without changing them, choose tag.

VocabularyFilterName
string | undefined

Specify the name of the custom vocabulary filter that you want to use when processing your transcription. Note that vocabulary filter names are case sensitive.

If the language of the specified custom vocabulary filter doesn't match the language identified in your media, the vocabulary filter is not applied to your transcription.

This parameter is not intended for use with the IdentifyLanguage parameter. If you're including IdentifyLanguage in your request and want to use one or more vocabulary filters with your transcription, use the VocabularyFilterNames parameter instead.

VocabularyFilterNames
string | undefined

Specify the names of the custom vocabulary filters that you want to use when processing your transcription. Note that vocabulary filter names are case sensitive.

If none of the languages of the specified custom vocabulary filters match the language identified in your media, your job fails.

This parameter is only intended for use with the IdentifyLanguage parameter. If you're not including IdentifyLanguage in your request and want to use a custom vocabulary filter with your transcription, use the VocabularyFilterName parameter instead.

VocabularyName
string | undefined

Specify the name of the custom vocabulary that you want to use when processing your transcription. Note that vocabulary names are case sensitive.

If the language of the specified custom vocabulary doesn't match the language identified in your media, the custom vocabulary is not applied to your transcription.

This parameter is not intended for use with the IdentifyLanguage parameter. If you're including IdentifyLanguage in your request and want to use one or more custom vocabularies with your transcription, use the VocabularyNames parameter instead.

For more information, see Custom vocabularies .

VocabularyNames
string | undefined

Specify the names of the custom vocabularies that you want to use when processing your transcription. Note that vocabulary names are case sensitive.

If none of the languages of the specified custom vocabularies match the language identified in your media, your job fails.

This parameter is only intended for use with the IdentifyLanguage parameter. If you're not including IdentifyLanguage in your request and want to use a custom vocabulary with your transcription, use the VocabularyName parameter instead.

For more information, see Custom vocabularies .

StartStreamTranscriptionCommand Output

Parameter
Type
Description
$metadata
Required
ResponseMetadata
Metadata pertaining to this request.
ContentIdentificationType
ContentIdentificationType | undefined

Shows whether content identification was enabled for your transcription.

ContentRedactionType
ContentRedactionType | undefined

Shows whether content redaction was enabled for your transcription.

EnableChannelIdentification
boolean | undefined

Shows whether channel identification was enabled for your transcription.

EnablePartialResultsStabilization
boolean | undefined

Shows whether partial results stabilization was enabled for your transcription.

IdentifyLanguage
boolean | undefined

Shows whether automatic language identification was enabled for your transcription.

IdentifyMultipleLanguages
boolean | undefined

Shows whether automatic multi-language identification was enabled for your transcription.

LanguageCode
LanguageCode | undefined

Provides the language code that you specified in your request.

LanguageModelName
string | undefined

Provides the name of the custom language model that you specified in your request.

LanguageOptions
string | undefined

Provides the language codes that you specified in your request.

MediaEncoding
MediaEncoding | undefined

Provides the media encoding you specified in your request.

MediaSampleRateHertz
number | undefined

Provides the sample rate that you specified in your request.

NumberOfChannels
number | undefined

Provides the number of channels that you specified in your request.

PartialResultsStability
PartialResultsStability | undefined

Provides the stabilization level used for your transcription.

PiiEntityTypes
string | undefined

Lists the PII entity types you specified in your request.

PreferredLanguage
LanguageCode | undefined

Provides the preferred language that you specified in your request.

RequestId
string | undefined

Provides the identifier for your streaming request.

SessionId
string | undefined

Provides the identifier for your transcription session.

ShowSpeakerLabel
boolean | undefined

Shows whether speaker partitioning was enabled for your transcription.

TranscriptResultStream
AsyncIterable<TranscriptResultStream> | undefined

Provides detailed information about your streaming session.

VocabularyFilterMethod
VocabularyFilterMethod | undefined

Provides the vocabulary filtering method used in your transcription.

VocabularyFilterName
string | undefined

Provides the name of the custom vocabulary filter that you specified in your request.

VocabularyFilterNames
string | undefined

Provides the names of the custom vocabulary filters that you specified in your request.

VocabularyName
string | undefined

Provides the name of the custom vocabulary that you specified in your request.

VocabularyNames
string | undefined

Provides the names of the custom vocabularies that you specified in your request.

Throws

Name
Fault
Details
BadRequestException
client

One or more arguments to the StartStreamTranscription, StartMedicalStreamTranscription, or StartCallAnalyticsStreamTranscription operation was not valid. For example, MediaEncoding or LanguageCode used unsupported values. Check the specified parameters and try your request again.

ConflictException
client

A new stream started with the same session ID. The current stream has been terminated.

InternalFailureException
server

A problem occurred while processing the audio. Amazon Transcribe terminated processing.

LimitExceededException
client

Your client has exceeded one of the Amazon Transcribe limits. This is typically the audio length limit. Break your audio stream into smaller chunks and try your request again.

ServiceUnavailableException
server

The service is currently unavailable. Try your request later.

TranscribeStreamingServiceException
Base exception class for all service exceptions from TranscribeStreaming service.