2024년 7월 기준으로 자동 마이그레이션된 프로젝트가 없습니다. 추가 안내가 있을 때까지 자동 마이그레이션은 보류 상태로 유지됩니다(ETA 없음).
기본 Speech-to-Text 모델을 계속 사용할 수 있지만 Conformer 기반 음성 모델을 선택하는 것이 좋습니다.
마이그레이션 개요
특정 언어 태그 및 음성 설정 조합을 사용하면 오디오가 포함된 대화형 에이전트(Dialogflow CX) 및 Dialogflow ES 트래픽이 점진적으로 command_and_search, default, phone_call, video 모델 식별자 뒤쪽의 기존 Speech-to-Text 모델에서 새로운 Conformer 기반 음성 모델로 라우팅됩니다. 리디렉션이 내부 전용이므로 현재 모델 식별자와 코드는 유효하게 유지되며 트래픽을 계속 처리합니다.
요청 수준 음성 모델 재정의 설정을 사용하는 경우를 제외하고 런타임에서 API에 지정된 음성 모델이 대화형 에이전트(Dialogflow CX) 콘솔에 지정된 음성 모델보다 우선 적용됩니다. 음성 모델의 우선순위에 대해 자세히 알아보세요.
파트너 전화 통합의 경우 음성 모델이 API에 설정되는지 전화 서비스 제공업체에 문의하세요. 대화형 에이전트(Dialogflow CX) Phone Gateway를 사용하는 경우 음성 모델 제한사항을 검토합니다.
프로젝트를 사전에 마이그레이션하면 충분한 시간을 갖고 모델을 테스트하고 일찍 개선된 정확성과 견고성을 활용할 수 있습니다. 이 방법은 특히 새 telephony 및 telephony_short 모델로 마이그레이션할 모델을 사용하는 경우에 권장됩니다. 대부분의 통합에는 single_utterance = true가 필요하므로 고급 제한 시간 기반 음성 종료 민감도를 사용하지 않는다면 telephony_short 또는 latest_short를 사용하는 경우가 많습니다.
[[["이해하기 쉬움","easyToUnderstand","thumb-up"],["문제가 해결됨","solvedMyProblem","thumb-up"],["기타","otherUp","thumb-up"]],[["이해하기 어려움","hardToUnderstand","thumb-down"],["잘못된 정보 또는 샘플 코드","incorrectInformationOrSampleCode","thumb-down"],["필요한 정보/샘플이 없음","missingTheInformationSamplesINeed","thumb-down"],["번역 문제","translationIssue","thumb-down"],["기타","otherDown","thumb-down"]],["최종 업데이트: 2025-09-04(UTC)"],[[["\u003cp\u003eDialogflow's audio traffic for specific language tags (including \u003ccode\u003een\u003c/code\u003e, \u003ccode\u003een-us\u003c/code\u003e, \u003ccode\u003ede\u003c/code\u003e, \u003ccode\u003ees\u003c/code\u003e, \u003ccode\u003efr\u003c/code\u003e, \u003ccode\u003eit\u003c/code\u003e, \u003ccode\u003eja\u003c/code\u003e, \u003ccode\u003enl\u003c/code\u003e, \u003ccode\u003ept-br\u003c/code\u003e, and their regional variants) will gradually shift from classic Speech-to-Text models to new conformer-based models, but current model identifiers remain valid.\u003c/p\u003e\n"],["\u003cp\u003eAutomatic migration is on hold indefinitely, and users can continue using the classic models.\u003c/p\u003e\n"],["\u003cp\u003eUsers are encouraged to proactively opt in to the new conformer-based speech models to benefit from potential improvements in accuracy and robustness.\u003c/p\u003e\n"],["\u003cp\u003eThe migration will affect the model identifier used for audio requests based on the language tag and the \u003ccode\u003esingle_utterance\u003c/code\u003e setting, with specific model identifier mappings provided for \u003ccode\u003een\u003c/code\u003e/\u003ccode\u003een-us\u003c/code\u003e and other affected language tags.\u003c/p\u003e\n"],["\u003cp\u003eThere is the option to change the model identifier in the Dialogflow CX API or Console's Advanced Speech Settings, and the API settings take precedence unless overridden.\u003c/p\u003e\n"]]],[],null,["# Speech model migration in Q1 2024\n\n| **Note:** This migration may affect you only if the client or integration you use sends audio requests to Dialogflow with the following language tags: `en`, `en-us`, `en-au`, `en-gb`, `en-in`, `de`, `es`, `es-es`, `es-us`, `fr`, `fr-ca`, `fr-fr`, `it`, `ja`, `nl`, `pt-br`.\n\nMigration status\n----------------\n\nAs of July 2024, no projects have been [automatically migrated](#automatic). The\nautomatic migration will remain on hold until further notice (no ETA).\n\nYou can continue to use the classic Speech-to-Text models but are encouraged to\n[opt in](#opt-in) to use conformer-based speech models.\n\nMigration overview\n------------------\n\nFor certain [language tag](/dialogflow/cx/docs/reference/language) and speech\nsetting combinations, the Conversational Agents (Dialogflow CX) and Dialogflow ES traffic with audio will\ngradually route away from the classic Speech-to-Text models behind the\n`command_and_search`, `default`, `phone_call`, and `video` model identifiers to\nthe new conformer-based [speech\nmodels](/speech-to-text/docs/transcription-model). As the redirection will be\ninternal only, the current model identifiers and code will remain valid and\ncontinue to serve traffic.\n\nThe tables in the [Migration for `en` and `en-us`language tags](#en-en-us) and\n[Migration for `de`, `en-au`, `en-gb`, `en-in`, `es`, `es-es`, `es-us`, `fr`,\n`fr-ca`, `fr-fr`, `it`, `ja`, `nl`, `pt-br` language\ntags](#non-en-en-us-affected) sections show the routing of Speech-to-Text\nmodels that will take place when the migration takes effect. If your\nconfiguration matches the language tag and the first two columns in the table,\nthe new model identifier is listed in the third column. No change is expected\nfor other configurations.\n\nSee the [Migration options](#options) section to choose the best option for you.\n\nMigration for `en` and `en-us` language tags\n--------------------------------------------\n\nMigration for `de`, `en-au`, `en-gb`, `en-in`, `es`, `es-es`, `es-us`, `fr`, `fr-ca`, `fr-fr`, `it`, `ja`, `nl`, `pt-br` language tags\n--------------------------------------------------------------------------------------------------------------------------------------\n\nMigration options\n-----------------\n\nThere are three migration options: early opt-in, automatic, and temporary\nopt-out.\n\n### Opt in and migrate earlier\n\nTo opt in proactively, change the speech model identifier that you have been\nusing in the [Conversational Agents (Dialogflow CX)\nAPI](/dialogflow/cx/docs/reference/rest/v3/ConversationTurn#inputaudioconfig)\nand [Dialogflow ES\nAPI](/dialogflow/es/docs/reference/rpc/google.cloud.dialogflow.v2#inputaudioconfig)\nwith the updated one. For Conversational Agents (Dialogflow CX), you can also change the [model\nidentifier](/dialogflow/cx/docs/concept/agent#stt-model-selection) in the\n**Advanced speech settings** under **Speech and IVR settings** in the\nConversational Agents (Dialogflow CX) console.\n\nSpeech model specified in the API at runtime takes precedence over the speech\nmodel specified in the Conversational Agents (Dialogflow CX) console, unless you enable the [**Override\nrequest-level speech\nmodel**](/dialogflow/cx/docs/concept/agent#stt-model-selection) setting. Read\nmore about precedence in [speech\nmodels](/dialogflow/cx/docs/concept/speech-models).\n\nFor partner telephony integrations, check with your telephony provider if the\nspeech model is being set in the API. If you are using the Conversational Agents (Dialogflow CX) Phone\nGateway, review the speech model\n[limitations](/dialogflow/cx/docs/concept/integration/phone-gateway#limits).\n\nMigrating your project proactively gives you time to test the models and take\nadvantage of the improved accuracy and robustness earlier. This approach is\nhighly recommended, especially if you are using a model that will\n[migrate](#en-en-us) to the new `telephony` and `telephony_short` models. Most\nintegrations require `single_utterance = true`, so if you are not using\n[advanced timeout-based end of speech sensitivity](/dialogflow/cx/docs/concept/agent#advanced-end-of-speech-sensitivity)\nyou'll likely want to use `telephony_short` or `latest_short`.\n\nIf you experience issues with the new models, [open a Google Cloud support\ncase](/support/docs/customer-care-procedures) with issue details.\n\n### Migrate automatically\n\n| **Note:** See [migration status](#status).\n\nTo be migrated automatically, no action is required on your part. The existing\nSpeech-to-Text model identifiers are valid and we will shift traffic\ninternally.\n\n### Opt out and migrate later\n\nDue to the suspended [migration status](#status), new opt-out requests are not\naccepted. If your projects were opted out before July 2024, they will remain in\nthis state until further announcement."]]
