Gunakan API HTTP Voice Design untuk membuat, menampilkan daftar, mengkueri, dan menghapus voice kustom.
Panduan pengguna: Voice Design.
Endpoint
Singapura
POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/audio/tts/customization
Ganti {WorkspaceId} dengan workspace ID Anda yang sebenarnya.
China (Beijing)
POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/audio/tts/customization
Ganti {WorkspaceId} dengan workspace ID Anda yang sebenarnya.
Penting Alibaba Cloud Model Studio telah merilis domain khusus ruang kerja untuk wilayah China (Beijing) dan Singapura. Domain khusus baru ini memberikan performa lebih unggul dan stabilitas lebih tinggi untuk permintaan inferensi. Kami merekomendasikan migrasi ke domain baru berikut:
Ganti {WorkspaceId} dengan Workspace ID Anda yang sebenarnya. Domain lama tetap berfungsi penuh.
Membuat suara
Isi permintaan
|
CosyVoice Voice Design hanya tersedia di wilayah Beijing. Qwen Voice Design mendukung wilayah Singapura. Contoh CosyVoice di bawah ini menggunakan URL wilayah China (Beijing). Contoh Qwen di bawah ini menggunakan URL wilayah Singapura (ganti {WorkspaceId} dengan workspace ID Anda yang sebenarnya).
CosyVoice voice designcurl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/audio/tts/customization \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "voice-enrollment",
"input": {
"action": "create_voice",
"target_model": "cosyvoice-v3.5-plus",
"voice_prompt": "A composed middle-aged male announcer with a deep, rich and magnetic voice, a steady speaking speed and clear articulation, is suitable for news broadcasting or documentary commentary.",
"preview_text": "Dear listeners, hello everyone. Welcome to the evening news.",
"prefix": "announcer",
"language_hints": ["en"]
},
"parameters": {
"sample_rate": 24000,
"response_format": "wav"
}
}'
Qwen voice designcurl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/audio/tts/customization \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen-voice-design",
"input": {
"action": "create",
"target_model": "qwen3-tts-vd-realtime-2026-01-15",
"preferred_name": "announcer",
"voice_prompt": "A composed middle-aged male announcer with a deep, rich and magnetic voice, a steady speaking speed and clear articulation, is suitable for news broadcasting or documentary commentary.",
"preview_text": "Dear listeners, hello everyone. Welcome to the evening news.",
"language": "en"
},
"parameters": {
"sample_rate": 24000,
"response_format": "wav"
}
}'
|
|
model string (Wajib)
Model voice design. Nilai yang valid:
|
|
|
|
parameters object (Opsional)
Konfigurasi untuk voice design.
Properti
sample_rate int (Opsional)
Laju sampel audio pratinjau, dalam Hz.
-
CosyVoice: 16.000, 24.000, atau 48.000.
-
Qwen: 8.000, 16.000, 24.000, atau 48.000.
Default: 24.000.
response_format string (Opsional)
Format audio pratinjau.
-
CosyVoice: pcm, wav, atau mp3.
-
Qwen: pcm, wav, mp3, atau opus.
Default: wav.
|
Isi respons
|
CosyVoice voice design{
"output": {
"preview_audio": {
"data": "{base64_encoded_audio}",
"sample_rate": 24000,
"response_format": "wav"
},
"target_model": "cosyvoice-v3.5-plus",
"voice_id": "cosyvoice-v3.5-plus-vd-announcer-xxxxxx"
},
"usage": {
"count": 1
},
"request_id": "xxxx-xxxx-xxxx"
}
Qwen voice design{
"output": {
"preview_audio": {
"data": "{base64_encoded_audio}",
"sample_rate": 24000,
"response_format": "wav"
},
"target_model": "qwen3-tts-vd-realtime-2026-01-15",
"voice": "yourVoice"
},
"usage": {
"count": 1
},
"request_id": "xxxx-xxxx-xxxx"
}
Penting
CosyVoice mengembalikan bidang voice_id, sedangkan Qwen mengembalikan bidang voice.
|
|
request_id string
Identifikasi unik dari permintaan ini.
|
|
output object
Data yang dikembalikan oleh model.
Properti
voice_id / voice string
ID voice. CosyVoice mengembalikan voice_id, dan Qwen mengembalikan voice. Gunakan nilai ini langsung sebagai parameter voice di API TTS.
preview_audio object
Data audio pratinjau.
Properti
data string
Data audio pratinjau, dienkripsi Base64.
sample_rate int
Laju sampel audio pratinjau, dalam Hz.
response_format string
Format audio pratinjau.
target_model string
Model TTS yang menghasilkan suara.
|
|
usage object
Informasi penggunaan untuk permintaan ini.
Properti
count integer
Jumlah voice yang dibuat. Selalu 1.
|
Daftar voice
Isi permintaan
|
CosyVoice Voice Design hanya tersedia di wilayah Beijing. Qwen Voice Design mendukung wilayah Singapura. Contoh CosyVoice di bawah ini menggunakan URL wilayah China (Beijing). Contoh Qwen di bawah ini menggunakan URL wilayah Singapura (ganti {WorkspaceId} dengan workspace ID Anda yang sebenarnya).
CosyVoicecurl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/audio/tts/customization \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "voice-enrollment",
"input": {
"action": "list_voice",
"prefix": "myvoice",
"page_size": 10,
"page_index": 0
}
}'
Qwen voice designcurl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/audio/tts/customization \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen-voice-design",
"input": {
"action": "list",
"page_size": 10,
"page_index": 0
}
}'
|
|
model string (Wajib)
Model voice design. Nilai yang valid:
|
|
|
Isi Respons
|
CosyVoice{
"output": {
"voice_list": [
{
"voice_id": "cosyvoice-v3.5-plus-vd-announcer-xxxxxx",
"gmt_create": "2025-12-10 14:54:09",
"gmt_modified": "2025-12-10 17:47:48",
"status": "OK",
"voice_prompt": "A composed middle-aged male announcer with a deep, rich and magnetic voice, a steady speaking speed and clear articulation, is suitable for news broadcasting or documentary commentary.",
"preview_text": "Dear listeners, hello everyone. Welcome to the evening news."
}
]
},
"usage": {
"count": 1
},
"request_id": "xxxx-xxxx-xxxx"
}
Qwen{
"output": {
"page_index": 0,
"page_size": 10,
"total_count": 1,
"voice_list": [
{
"voice": "yourVoice",
"gmt_create": "2025-08-11 17:59:32",
"gmt_modified": "2025-08-11 17:59:32",
"language": "zh",
"target_model": "qwen3-tts-vd-realtime-2026-01-15",
"voice_prompt": "A composed middle-aged male announcer with a deep, rich and magnetic voice, a steady speaking speed and clear articulation, is suitable for news broadcasting or documentary commentary.",
"preview_text": "Dear listeners, hello everyone. Welcome to the evening news."
}
]
},
"usage": {
"count": 0
},
"request_id": "xxxx-xxxx-xxxx"
}
Penting
CosyVoice mengembalikan array voice_list di mana setiap item berisi bidang voice_id. Qwen juga mengembalikan array voice_list, tetapi setiap item berisi bidang voice sebagai gantinya. Output Qwen juga mencakup bidang paginasi page_index, page_size, dan total_count.
|
|
request_id string
Identifikasi unik dari permintaan ini.
|
|
output object
Data yang dikembalikan oleh model.
Properti
page_index integer
Penting
Hanya dikembalikan oleh Qwen.
Indeks halaman saat ini.
page_size integer
Penting
Hanya dikembalikan oleh Qwen.
Jumlah entri per halaman.
total_count integer
Penting
Hanya dikembalikan oleh Qwen.
Total jumlah suara.
voice_list array[object]
Daftar voice yang dikembalikan oleh kueri.
Properti
voice_id / voice string
ID voice. CosyVoice menggunakan voice_id, dan Qwen menggunakan voice.
gmt_create string
Waktu pembuatan.
gmt_modified string
Waktu modifikasi terakhir.
status string
Penting
Hanya dikembalikan oleh CosyVoice.
Status voice. Untuk nilai yang valid, lihat "Referensi status voice".
target_model string
Penting
Hanya dikembalikan oleh Qwen.
Model TTS yang menggerakkan voice.
language string
Bahasa suara.
voice_prompt string
Teks deskripsi voice.
preview_text string
Teks audio pratinjau.
|
|
usage object
Informasi penggunaan untuk permintaan ini.
Properti
count integer
CosyVoice: selalu 1. Qwen: selalu 0.
|
Kueri detail voice
Badan permintaan
|
CosyVoice Voice Design hanya tersedia di wilayah Beijing. Qwen Voice Design mendukung wilayah Singapura. Contoh CosyVoice di bawah ini menggunakan URL wilayah China (Beijing). Contoh Qwen di bawah ini menggunakan URL wilayah Singapura (ganti {WorkspaceId} dengan workspace ID Anda yang sebenarnya).
CosyVoicecurl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/audio/tts/customization \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "voice-enrollment",
"input": {
"action": "query_voice",
"voice_id": "yourVoiceId"
}
}'
Qwen voice designcurl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/audio/tts/customization \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen-voice-design",
"input": {
"action": "query",
"voice": "yourVoice"
}
}'
|
|
model string (Wajib)
Model voice design. Nilai yang valid:
|
|
|
Isi respons
|
CosyVoice voice design{
"output": {
"voice_id": "cosyvoice-v3.5-plus-vd-announcer-xxxxxx",
"gmt_create": "2025-12-10 14:54:09",
"gmt_modified": "2025-12-10 17:47:48",
"preview_text": "Dear listeners, hello everyone. Welcome to the evening news.",
"target_model": "cosyvoice-v3.5-plus",
"status": "OK",
"voice_prompt": "A composed middle-aged male announcer with a deep, rich and magnetic voice, a steady speaking speed and clear articulation, is suitable for news broadcasting or documentary commentary."
},
"usage": {},
"request_id": "xxxx-xxxx-xxxx"
}
Qwen voice design{
"output": {
"voice": "yourVoice",
"gmt_create": "2025-08-11 17:59:32",
"gmt_modified": "2025-08-11 17:59:32",
"language": "zh",
"target_model": "qwen3-tts-vd-realtime-2026-01-15"
},
"usage": {
"count": 0
},
"request_id": "xxxx-xxxx-xxxx"
}
Penting
CosyVoice mengembalikan voice_id, voice_prompt, dan bidang lainnya. Qwen mengembalikan bidang voice dan language.
|
|
request_id string
Identifikasi unik dari permintaan ini.
|
|
output object
Data yang dikembalikan oleh model.
Properti
voice_id / voice string
ID voice. CosyVoice mengembalikan voice_id, dan Qwen mengembalikan voice.
gmt_create string
Waktu pembuatan.
gmt_modified string
Waktu modifikasi terakhir.
status string
Penting
Hanya dikembalikan oleh CosyVoice.
Status voice. Untuk nilai yang valid, lihat "Referensi status voice".
target_model string
Model TTS yang menggerakkan voice.
language string
Penting
Hanya dikembalikan oleh Qwen voice design.
Bahasa voice.
voice_prompt string
Penting
Hanya dikembalikan oleh CosyVoice voice design.
Teks deskripsi audio.
preview_text string
Penting
Hanya dikembalikan oleh CosyVoice voice design.
Teks audio pratinjau.
|
|
usage object
Informasi penggunaan untuk permintaan ini.
Properti
count integer
Qwen: selalu 0. Tidak dikembalikan oleh CosyVoice (objek usage kosong).
|
Hapus suara
Isi permintaan
|
CosyVoice Voice Design hanya tersedia di wilayah Beijing. Qwen Voice Design mendukung wilayah Singapura. Contoh CosyVoice di bawah ini menggunakan URL wilayah China (Beijing). Contoh Qwen di bawah ini menggunakan URL wilayah Singapura (ganti {WorkspaceId} dengan workspace ID Anda yang sebenarnya).
CosyVoicecurl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/audio/tts/customization \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "voice-enrollment",
"input": {
"action": "delete_voice",
"voice_id": "yourVoiceId"
}
}'
Qwen voice designcurl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/audio/tts/customization \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen-voice-design",
"input": {
"action": "delete",
"voice": "yourVoice"
}
}'
|
|
model string (Wajib)
Model voice design. Nilai yang valid:
|
|
|
Isi respons
|
CosyVoice{
"output": {},
"usage": {
"count": 1
},
"request_id": "xxxx-xxxx-xxxx"
}
Qwen{
"output": {
"voice": "yourVoice"
},
"usage": {
"count": 0
},
"request_id": "xxxx-xxxx-xxxx"
}
Penting
CosyVoice mengembalikan objek output kosong, sedangkan Qwen mengembalikan bidang voice.
|
|
request_id string
Identifikasi unik dari permintaan ini.
|
|
output object
Data yang dikembalikan oleh model. CosyVoice mengembalikan objek kosong. Qwen mengembalikan nama voice yang dihapus.
Properti
voice string
Penting
Hanya dikembalikan oleh Qwen.
Nama voice yang dihapus.
|
|
usage object
Informasi penggunaan untuk permintaan ini.
Properti
count integer
CosyVoice: selalu 1. Qwen: selalu 0.
|
Referensi status voice
Setelah voice dibuat, voice tersebut melewati proses peninjauan. Tabel berikut menjelaskan setiap status. Sistem status ini hanya berlaku untuk CosyVoice (ketika model adalah voice-enrollment). Respons kueri dan daftar Qwen tidak menyertakan bidang status.
|
Status
|
Deskripsi
|
|
DEPLOYING
|
Dalam peninjauan atau pemrosesan.
|
|
OK
|
Peninjauan lolos. Voice siap digunakan.
|
|
UNDEPLOYED
|
Peninjauan ditolak. Voice tidak dapat digunakan.
|