Beberapa produk dan fitur sedang dalam proses penggantian nama. Fitur playbook dan alur generatif juga dimigrasikan ke satu konsol gabungan. Lihat detailnya.
Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
Status migrasi
Mulai Juli 2024, tidak ada project yang telah dimigrasikan secara otomatis. Migrasi otomatis akan tetap ditangguhkan hingga pemberitahuan lebih lanjut (tidak ada perkiraan waktu penyelesaian).
Anda dapat terus menggunakan model Speech-to-Text klasik, tetapi sebaiknya
ikut serta menggunakan model ucapan berbasis konformer.
Ringkasan migrasi
Untuk kombinasi tag bahasa dan setelan
ucapan tertentu, traffic Agen Percakapan (Dialogflow CX) dan Dialogflow ES dengan audio akan
secara bertahap dialihkan dari model Speech-to-Text klasik di balik
ID model command_and_search, default, phone_call, dan video ke
model
ucapan berbasis konformer baru. Karena pengalihan hanya akan
bersifat internal, ID dan kode model saat ini akan tetap valid dan
terus menayangkan traffic.
Ada tiga opsi migrasi: keikutsertaan awal, otomatis, dan tidak ikut sementara.
Memilih ikut serta dan melakukan migrasi lebih awal
Untuk memilih ikut serta secara proaktif, ubah ID model ucapan yang telah Anda
gunakan di Conversational Agents (Dialogflow CX)
API
dan Dialogflow ES
API
dengan yang telah diperbarui. Untuk Agen Percakapan (Dialogflow CX), Anda juga dapat mengubah ID
model di
Setelan ucapan lanjutan di bagian Setelan ucapan dan IVR di
konsol Agen Percakapan (Dialogflow CX).
Model ucapan yang ditentukan di API saat runtime lebih diutamakan daripada model
ucapan yang ditentukan di konsol Agen Percakapan (Dialogflow CX), kecuali jika Anda mengaktifkan setelan Ganti
model ucapan
tingkat permintaan. Baca
selengkapnya tentang prioritas dalam model
ucapan.
Untuk integrasi telepon partner, hubungi penyedia telepon Anda untuk mengetahui apakah
model ucapan disetel di API. Jika Anda menggunakan Gateway
Ponsel Agen Percakapan (Dialogflow CX), tinjau batasan
model ucapan.
Melakukan migrasi project secara proaktif memberi Anda waktu untuk menguji model dan memanfaatkan
akurasi dan keandalan yang lebih baik lebih awal. Pendekatan ini
sangat direkomendasikan, terutama jika Anda menggunakan model yang akan
bermigrasi ke model telephony dan telephony_short baru. Sebagian besar
integrasi memerlukan single_utterance = true, jadi jika Anda tidak menggunakan
sensitivitas akhir ucapan berbasis waktu tunggu lanjutan,
Anda mungkin ingin menggunakan telephony_short atau latest_short.
Anda tidak perlu melakukan tindakan apa pun agar dapat dimigrasikan secara otomatis. ID model Ucapan ke Teks yang ada valid dan kami akan mengalihkan traffic secara internal.
Memilih tidak ikut serta dan bermigrasi nanti
Karena status migrasi ditangguhkan, permintaan keikutsertaan baru tidak
diterima. Jika project Anda tidak diikutsertakan sebelum Juli 2024, project tersebut akan tetap dalam
status ini hingga pengumuman lebih lanjut.
[[["Mudah dipahami","easyToUnderstand","thumb-up"],["Memecahkan masalah saya","solvedMyProblem","thumb-up"],["Lainnya","otherUp","thumb-up"]],[["Sulit dipahami","hardToUnderstand","thumb-down"],["Informasi atau kode contoh salah","incorrectInformationOrSampleCode","thumb-down"],["Informasi/contoh yang saya butuhkan tidak ada","missingTheInformationSamplesINeed","thumb-down"],["Masalah terjemahan","translationIssue","thumb-down"],["Lainnya","otherDown","thumb-down"]],["Terakhir diperbarui pada 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."]]
