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.
Saat menggunakan text-to-speech untuk agen Anda, Anda dapat membuat model suara yang dipersonalisasi dengan melatih model menggunakan rekaman audio Anda sendiri.
Batasan
Fitur ini hanya tersedia untuk bahasa dan lokalitas berikut:
ar-XA
cmn-CN
de-DE
en-AU
en-GB
en-IN
en-US
es-ES
es-US
fr-CA
fr-FR
gu-IN
hi-IN
id-ID
it-IT
ko-KR
mr-IN
nl-NL
pl-PL
pt-BR
ru-RU
ta-IN
te-IN
th-TH
tr-TR
ur-IN
vi-VN
Konfigurasi
Untuk mengonfigurasi kloning suara:
Fitur ini disediakan melalui produk Text-to-Speech,
dan saat ini akses fitur ini dibatasi.
Lihat
petunjuk untuk meminta akses.
Latih model Anda.
Saat membuat model, salin kunci suara.
Anda akan memerlukan nilai ini untuk mengonfigurasi agen.
Buka setelan agen Conversational Agents (Dialogflow CX),
pilih tab Speech and IVR,
lalu scroll ke bawah ke Voice selection.
Untuk nama suara, pilih Suara yang dikloning.
Untuk kunci suara,
tempelkan kunci suara yang Anda salin di atas.
Anda dapat mengklik tombol Uji kunci untuk memverifikasi bahwa kunci tersebut valid.
[[["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."],[],[],null,["# Voice cloning\n\n| **Preview**\n|\n|\n| This product or feature is subject to the \"Pre-GA Offerings Terms\" in the General Service Terms section\n| of the [Service Specific Terms](/terms/service-terms#1).\n|\n| Pre-GA products and features are available \"as is\" and might have limited support.\n|\n| For more information, see the\n| [launch stage descriptions](/products#product-launch-stages).\n\nWhen using text-to-speech for your agent,\nyou can create personalized voice models by training a model with your own\naudio recordings.\n\nLimitations\n-----------\n\nThis feature is only available for the following languages and locales:\n\n- ar-XA\n- cmn-CN\n- de-DE\n- en-AU\n- en-GB\n- en-IN\n- en-US\n- es-ES\n- es-US\n- fr-CA\n- fr-FR\n- gu-IN\n- hi-IN\n- id-ID\n- it-IT\n- ko-KR\n- mr-IN\n- nl-NL\n- pl-PL\n- pt-BR\n- ru-RU\n- ta-IN\n- te-IN\n- th-TH\n- tr-TR\n- ur-IN\n- vi-VN\n\nConfiguration\n-------------\n\nTo configure a voice cloning:\n\n1. This feature is provided via the Text-to-Speech product, and the feature is currently restricted access. See the [instructions for requesting access](/text-to-speech/docs/chirp3-instant-custom-voice).\n2. [Train your model](/text-to-speech/docs/chirp3-instant-custom-voice#use_chirp_3_instant_custom_voice). When creating your model, copy the voice key. You will need this value to configure your agent.\n3. Go to the Conversational Agents (Dialogflow CX) agent settings, select the **Speech and IVR** tab, then scroll down to **Voice selection**.\n4. For the voice name, select **Cloned voice**.\n5. For the voice key, paste the voice key you copied above.\n6. You can click the **Test key** button to verify that the key is valid."]]
