---
title: "PUT /bots/{botId}/botversions/{botVersion}/botlocales/{localeId}/"
method: PUT
path: "/bots/{botId}/botversions/{botVersion}/botlocales/{localeId}/"
---

# PUT /bots/{botId}/botversions/{botVersion}/botlocales/{localeId}/

`PUT /bots/{botId}/botversions/{botVersion}/botlocales/{localeId}/`

Updates the settings that a bot has for a specific locale.

## Path parameters

- `botId` string, required
- `botVersion` string, required
- `localeId` string, required

## Request body

- object
  - `description` string — The new description of the locale.
  - `nluIntentConfidenceThreshold` number, double, required — The new confidence threshold where Amazon Lex inserts the <code>AMAZON.FallbackIntent</code> and <code>AMAZON.KendraSearchIntent</code> intents in the list of possible intents for an utterance.
  - `voiceSettings` object — <p>Defines settings for using an Amazon Polly voice to communicate with a user.</p> <p>Valid values include:</p> <ul> <li> <p> <code>standard</code> </p> </li> <li> <p> <code>neural</code> </p> </li> <li> <p> <code>long-form</code> </p> </li> <li> <p> <code>generative</code> </p> </li> </ul>
    - `engine` 'standard' | 'neural' | 'long-form' | 'generative' — <p>Indicates the type of Amazon Polly voice that Amazon Lex should use for voice interaction with the user. For more information, see the <a href="https://docs.aws.amazon.com/polly/latest/dg/API_SynthesizeSpeech.html#polly-SynthesizeSpeech-request-Engine"> <code>engine</code> parameter of the <code>SynthesizeSpeech</code> operation</a> in the <i>Amazon Polly developer guide</i>.</p> <p>If you do not specify a value, the default is <code>standard</code>.</p>
    - `voiceId` string — The identifier of the Amazon Polly voice to use.
  - `unifiedSpeechSettings` object — Unified configuration settings that combine speech recognition and synthesis capabilities.
    - `speechFoundationModel` object — The foundation model configuration to use for unified speech processing capabilities.
      - `modelArn` string, required — The Amazon Resource Name (ARN) of the foundation model used for speech processing.
      - `voiceId` string — The identifier of the voice to use for speech synthesis with the foundation model.
  - `audioFillerSettings` object — <p>Configuration that plays background filler audio during speech-to-speech interactions to mask processing delays and improve the perceived responsiveness of the bot.</p> <p>Audio filler requires <code>unifiedSpeechSettings</code> (speech-to-speech) to be enabled on the bot locale when <code>enabled</code> is <code>true</code>.</p>
    - `enabled` boolean — Specifies whether audio filler playback is enabled for the bot locale. Set to <code>true</code> to play filler audio while Amazon Lex processes a user utterance. Set to <code>false</code> to disable filler audio.
    - `audioType` 'MELODY_CHIPPER_CHIME' | 'MELODY_CURIOUS_CRAWL' | 'MELODY_RISING_RIPPLE' | 'MELODY_PATIENT_PING' | 'MELODY_PONDERING_PONG' | 'TYPING_KINETIC_KEYS' | 'TYPING_QUIET_QWERTY' — The identifier of the audio filler to play while Amazon Lex processes the user's input. This field is required when <code>enabled</code> is <code>true</code>.
    - `startDelayInMilliseconds` integer — The time, in milliseconds, to wait after the end of the user's utterance before starting audio filler playback. Valid range is <code>500</code> to <code>5000</code> milliseconds. If not specified, Amazon Lex uses a default of <code>2500</code> milliseconds.
    - `minimumPlayDurationInMilliseconds` integer — The minimum time, in milliseconds, that audio filler plays once it has started, even if the bot response becomes ready sooner. Valid range is <code>1000</code> to <code>5000</code> milliseconds. If not specified, Amazon Lex uses a default of <code>3000</code> milliseconds.
    - `responseDeliveryDelayInMilliseconds` integer — The silent delay, in milliseconds, inserted between the end of audio filler playback and the start of the bot's response. Valid range is <code>200</code> to <code>1000</code> milliseconds. If not specified, Amazon Lex uses a default of <code>500</code> milliseconds.
  - `speechRecognitionSettings` object — Settings that control how Amazon Lex processes and recognizes speech input from users.
    - `speechModelPreference` 'Standard' | 'Neural' | 'Deepgram' — The speech-to-text model to use.
    - `speechModelConfig` object — Configuration settings for the selected speech-to-text model.
      - `deepgramConfig` object — Configuration settings for using Deepgram as the speech-to-text provider.
        - `apiTokenSecretArn` string, required — The Amazon Resource Name (ARN) of the Secrets Manager secret that contains the Deepgram API token.
        - `modelId` string — The identifier of the Deepgram speech-to-text model to use for processing speech input.
  - `generativeAISettings` object — Contains specifications about the generative AI capabilities from Amazon Bedrock that you can turn on for your bot.
    - `runtimeSettings` RuntimeSettings — Contains specifications about the Amazon Lex runtime generative AI capabilities from Amazon Bedrock that you can turn on for your bot.
      - `slotResolutionImprovement` object — An object containing specifications for the assisted slot resolution feature.
        - `enabled` boolean, required — Specifies whether assisted slot resolution is turned on or off.
        - `bedrockModelSpecification` object — An object containing information about the Amazon Bedrock model used to assist slot resolution.
          - `modelArn` string, required — The ARN of the foundation model used in descriptive bot building.
          - `guardrail` object — The guardrail configuration in the Bedrock model specification details.
            - `identifier` string, required — The unique guardrail id for the Bedrock guardrail configuration.
            - `version` string, required — The guardrail version for the Bedrock guardrail configuration.
          - `traceStatus` 'ENABLED' | 'DISABLED' — The Bedrock trace status in the Bedrock model specification details.
          - `customPrompt` string — The custom prompt used in the Bedrock model specification details.
      - `nluImprovement` object — An object containing specifications for the Assisted NLU feature within the bot's runtime settings. These settings determine how the bot processes and interprets user utterances during conversations.
        - `enabled` boolean, required — Determines whether the Assisted NLU feature is enabled for the bot. When set to <code>true</code>, Amazon Lex uses advanced models to improve intent recognition and slot resolution, with the default being <code>false</code>.
        - `assistedNluMode` 'Primary' | 'Fallback' — Specifies the mode for Assisted NLU operation. Use <code>Primary</code> to make Assisted NLU the primary intent recognition method, or <code>Fallback</code> to use it only when standard NLU confidence is low.
        - `intentDisambiguationSettings` object — An object containing specifications for the Intent Disambiguation feature within the Assisted NLU settings. These settings determine how the bot handles ambiguous user inputs that could match multiple intents.
          - `enabled` boolean, required — Determines whether the Intent Disambiguation feature is enabled. When set to <code>true</code>, Amazon Lex will present disambiguation options to users when multiple intents could match their input, with the default being <code>false</code>.
          - `maxDisambiguationIntents` integer — Specifies the maximum number of intent options (2-5) to present to users when disambiguation is needed. This setting determines how many intent options will be shown to users when the system detects ambiguous input. The default value is 3.
          - `customDisambiguationMessage` string — Provides a custom message that will be displayed before presenting the disambiguation options to users. This message helps set the context for users and can be customized to match your bot's tone and brand. If not specified, a default message will be used.
    - `buildtimeSettings` BuildtimeSettings — Contains specifications about the Amazon Lex build time generative AI capabilities from Amazon Bedrock that you can turn on for your bot.
      - `descriptiveBotBuilder` object — An object containing specifications for the descriptive bot building feature.
        - `enabled` boolean, required — Specifies whether the descriptive bot building feature is activated or not.
        - `bedrockModelSpecification` object — An object containing information about the Amazon Bedrock model used to interpret the prompt used in descriptive bot building.
          - `modelArn` string, required — The ARN of the foundation model used in descriptive bot building.
          - `guardrail` object — The guardrail configuration in the Bedrock model specification details.
            - `identifier` string, required — The unique guardrail id for the Bedrock guardrail configuration.
            - `version` string, required — The guardrail version for the Bedrock guardrail configuration.
          - `traceStatus` 'ENABLED' | 'DISABLED' — The Bedrock trace status in the Bedrock model specification details.
          - `customPrompt` string — The custom prompt used in the Bedrock model specification details.
      - `sampleUtteranceGeneration` object — Contains specifications for the sample utterance generation feature.
        - `enabled` boolean, required — Specifies whether to enable sample utterance generation or not.
        - `bedrockModelSpecification` BedrockModelSpecification — Contains information about the Amazon Bedrock model used to interpret the prompt used in descriptive bot building.
          - `modelArn` string, required — The ARN of the foundation model used in descriptive bot building.
          - `guardrail` object — The guardrail configuration in the Bedrock model specification details.
            - `identifier` string, required — The unique guardrail id for the Bedrock guardrail configuration.
            - `version` string, required — The guardrail version for the Bedrock guardrail configuration.
          - `traceStatus` 'ENABLED' | 'DISABLED' — The Bedrock trace status in the Bedrock model specification details.
          - `customPrompt` string — The custom prompt used in the Bedrock model specification details.
  - `speechDetectionSensitivity` 'Default' | 'HighNoiseTolerance' | 'MaximumNoiseTolerance' — <p>Determines the sensitivity level for voice activity detection (VAD) in noisy environments. This setting helps optimize speech recognition accuracy by adjusting how the system responds to background noise.</p> <p>Valid values include:</p> <ul> <li> <p> <code>Default</code> - Standard sensitivity level suitable for most environments</p> </li> <li> <p> <code>HighNoiseTolerance</code> - Increased tolerance for moderate background noise</p> </li> <li> <p> <code>MaximumNoiseTolerance</code> - Maximum tolerance for high levels of background noise</p> </li> </ul>

## Response `202`

Success

- UpdateBotLocaleResponse
  - `botId` string — The identifier of the bot that contains the updated locale.
  - `botVersion` string — The version of the bot that contains the updated locale.
  - `localeId` string — The language and locale of the updated bot locale.
  - `localeName` string — The updated locale name for the locale.
  - `description` string — The updated description of the locale.
  - `nluIntentConfidenceThreshold` number, double — The updated confidence threshold for inserting the <code>AMAZON.FallbackIntent</code> and <code>AMAZON.KendraSearchIntent</code> intents in the list of possible intents for an utterance.
  - `voiceSettings` object — The updated Amazon Polly voice to use for voice interaction with the user.
    - `engine` 'standard' | 'neural' | 'long-form' | 'generative' — <p>Indicates the type of Amazon Polly voice that Amazon Lex should use for voice interaction with the user. For more information, see the <a href="https://docs.aws.amazon.com/polly/latest/dg/API_SynthesizeSpeech.html#polly-SynthesizeSpeech-request-Engine"> <code>engine</code> parameter of the <code>SynthesizeSpeech</code> operation</a> in the <i>Amazon Polly developer guide</i>.</p> <p>If you do not specify a value, the default is <code>standard</code>.</p>
    - `voiceId` string, required — The identifier of the Amazon Polly voice to use.
  - `unifiedSpeechSettings` object — The updated unified speech settings for the bot locale.
    - `speechFoundationModel` object, required — The foundation model configuration to use for unified speech processing capabilities.
      - `modelArn` string, required — The Amazon Resource Name (ARN) of the foundation model used for speech processing.
      - `voiceId` string — The identifier of the voice to use for speech synthesis with the foundation model.
  - `audioFillerSettings` object — The updated audio filler settings for the bot locale.
    - `enabled` boolean — Specifies whether audio filler playback is enabled for the bot locale. Set to <code>true</code> to play filler audio while Amazon Lex processes a user utterance. Set to <code>false</code> to disable filler audio.
    - `audioType` 'MELODY_CHIPPER_CHIME' | 'MELODY_CURIOUS_CRAWL' | 'MELODY_RISING_RIPPLE' | 'MELODY_PATIENT_PING' | 'MELODY_PONDERING_PONG' | 'TYPING_KINETIC_KEYS' | 'TYPING_QUIET_QWERTY' — The identifier of the audio filler to play while Amazon Lex processes the user's input. This field is required when <code>enabled</code> is <code>true</code>.
    - `startDelayInMilliseconds` integer — The time, in milliseconds, to wait after the end of the user's utterance before starting audio filler playback. Valid range is <code>500</code> to <code>5000</code> milliseconds. If not specified, Amazon Lex uses a default of <code>2500</code> milliseconds.
    - `minimumPlayDurationInMilliseconds` integer — The minimum time, in milliseconds, that audio filler plays once it has started, even if the bot response becomes ready sooner. Valid range is <code>1000</code> to <code>5000</code> milliseconds. If not specified, Amazon Lex uses a default of <code>3000</code> milliseconds.
    - `responseDeliveryDelayInMilliseconds` integer — The silent delay, in milliseconds, inserted between the end of audio filler playback and the start of the bot's response. Valid range is <code>200</code> to <code>1000</code> milliseconds. If not specified, Amazon Lex uses a default of <code>500</code> milliseconds.
  - `speechRecognitionSettings` object — The updated speech-to-text settings for the bot locale.
    - `speechModelPreference` 'Standard' | 'Neural' | 'Deepgram' — The speech-to-text model to use.
    - `speechModelConfig` object — Configuration settings for the selected speech-to-text model.
      - `deepgramConfig` object — Configuration settings for using Deepgram as the speech-to-text provider.
        - `apiTokenSecretArn` string, required — The Amazon Resource Name (ARN) of the Secrets Manager secret that contains the Deepgram API token.
        - `modelId` string — The identifier of the Deepgram speech-to-text model to use for processing speech input.
  - `botLocaleStatus` 'Creating' | 'Building' | 'Built' | 'ReadyExpressTesting' | 'Failed' | 'Deleting' | 'NotBuilt' | 'Importing' | 'Processing' — The current status of the locale. When the bot status is <code>Built</code> the locale is ready for use.
  - `failureReasons` FailureReason[] — If the <code>botLocaleStatus</code> is <code>Failed</code>, the <code>failureReasons</code> field lists the errors that occurred while building the bot.
  - `creationDateTime` string, date-time — A timestamp of the date and time that the locale was created.
  - `lastUpdatedDateTime` string, date-time — A timestamp of the date and time that the locale was last updated.
  - `recommendedActions` RecommendedAction[] — Recommended actions to take to resolve an error in the <code>failureReasons</code> field.
  - `generativeAISettings` object — Contains settings for generative AI features powered by Amazon Bedrock for your bot locale.
    - `runtimeSettings` RuntimeSettings — Contains specifications about the Amazon Lex runtime generative AI capabilities from Amazon Bedrock that you can turn on for your bot.
      - `slotResolutionImprovement` object — An object containing specifications for the assisted slot resolution feature.
        - `enabled` boolean, required — Specifies whether assisted slot resolution is turned on or off.
        - `bedrockModelSpecification` object — An object containing information about the Amazon Bedrock model used to assist slot resolution.
          - `modelArn` string, required — The ARN of the foundation model used in descriptive bot building.
          - `guardrail` object — The guardrail configuration in the Bedrock model specification details.
            - `identifier` string, required — The unique guardrail id for the Bedrock guardrail configuration.
            - `version` string, required — The guardrail version for the Bedrock guardrail configuration.
          - `traceStatus` 'ENABLED' | 'DISABLED' — The Bedrock trace status in the Bedrock model specification details.
          - `customPrompt` string — The custom prompt used in the Bedrock model specification details.
      - `nluImprovement` object — An object containing specifications for the Assisted NLU feature within the bot's runtime settings. These settings determine how the bot processes and interprets user utterances during conversations.
        - `enabled` boolean, required — Determines whether the Assisted NLU feature is enabled for the bot. When set to <code>true</code>, Amazon Lex uses advanced models to improve intent recognition and slot resolution, with the default being <code>false</code>.
        - `assistedNluMode` 'Primary' | 'Fallback' — Specifies the mode for Assisted NLU operation. Use <code>Primary</code> to make Assisted NLU the primary intent recognition method, or <code>Fallback</code> to use it only when standard NLU confidence is low.
        - `intentDisambiguationSettings` object — An object containing specifications for the Intent Disambiguation feature within the Assisted NLU settings. These settings determine how the bot handles ambiguous user inputs that could match multiple intents.
          - `enabled` boolean, required — Determines whether the Intent Disambiguation feature is enabled. When set to <code>true</code>, Amazon Lex will present disambiguation options to users when multiple intents could match their input, with the default being <code>false</code>.
          - `maxDisambiguationIntents` integer — Specifies the maximum number of intent options (2-5) to present to users when disambiguation is needed. This setting determines how many intent options will be shown to users when the system detects ambiguous input. The default value is 3.
          - `customDisambiguationMessage` string — Provides a custom message that will be displayed before presenting the disambiguation options to users. This message helps set the context for users and can be customized to match your bot's tone and brand. If not specified, a default message will be used.
    - `buildtimeSettings` BuildtimeSettings — Contains specifications about the Amazon Lex build time generative AI capabilities from Amazon Bedrock that you can turn on for your bot.
      - `descriptiveBotBuilder` object — An object containing specifications for the descriptive bot building feature.
        - `enabled` boolean, required — Specifies whether the descriptive bot building feature is activated or not.
        - `bedrockModelSpecification` object — An object containing information about the Amazon Bedrock model used to interpret the prompt used in descriptive bot building.
          - `modelArn` string, required — The ARN of the foundation model used in descriptive bot building.
          - `guardrail` object — The guardrail configuration in the Bedrock model specification details.
            - `identifier` string, required — The unique guardrail id for the Bedrock guardrail configuration.
            - `version` string, required — The guardrail version for the Bedrock guardrail configuration.
          - `traceStatus` 'ENABLED' | 'DISABLED' — The Bedrock trace status in the Bedrock model specification details.
          - `customPrompt` string — The custom prompt used in the Bedrock model specification details.
      - `sampleUtteranceGeneration` object — Contains specifications for the sample utterance generation feature.
        - `enabled` boolean, required — Specifies whether to enable sample utterance generation or not.
        - `bedrockModelSpecification` BedrockModelSpecification — Contains information about the Amazon Bedrock model used to interpret the prompt used in descriptive bot building.
          - `modelArn` string, required — The ARN of the foundation model used in descriptive bot building.
          - `guardrail` object — The guardrail configuration in the Bedrock model specification details.
            - `identifier` string, required — The unique guardrail id for the Bedrock guardrail configuration.
            - `version` string, required — The guardrail version for the Bedrock guardrail configuration.
          - `traceStatus` 'ENABLED' | 'DISABLED' — The Bedrock trace status in the Bedrock model specification details.
          - `customPrompt` string — The custom prompt used in the Bedrock model specification details.
  - `speechDetectionSensitivity` 'Default' | 'HighNoiseTolerance' | 'MaximumNoiseTolerance' — The updated sensitivity level for voice activity detection (VAD) in the bot locale.

## Other responses

- `480` — ThrottlingException
- `481` — ServiceQuotaExceededException
- `482` — ValidationException
- `483` — PreconditionFailedException
- `484` — ConflictException
- `485` — InternalServerException

---

[API](https://skmtc.net/aws/apis/lexv2-models.md) · [All operations](https://skmtc.net/aws/apis/lexv2-models/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/aws/lexv2-models/versions/6997ba482d72/schema)