Ruka hadi kwenye maudhui

VibeVoice 1.5B

Unganisha

Kitambulisho cha modeli vibevoice
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/vibevoice?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "speakers": [
      {
        "preset": "Frank [EN]"
      },
      {
        "preset": "Carter [EN]"
      }
    ]
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Ombi hili: ≈$ 0.02 salio za API 20 · ≈ ₽ 2.11 Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
Microsoft Maandishi hadi Matamshi #text-to-speech#multi-speaker#podcast

Ubadilishaji wa maandishi kuwa sauti kwa wazungumzaji wengi kwa hati ndefu kama podikasti, ukiwa na sauti kwa kila mzungumzaji

Microsoft · Sauti

Tokeo lako la kwanza linaonekana hapa

Unda ombi hapa chini na uliendeshe kwa ufunguo wako wa API. Matokeo yanakiliwa kwenye hifadhi yetu, yakihifadhiwa milele au 7 siku bila malipo.

Unda ombi

Vidhibiti vinazalishwa kutoka kwenye schema ya modeli. Msimbo na bei husasishwa unapovibadilisha.

•inahitajika 88 / 90000

Script ya ingizo la sauti, yenye lebo za hiari za 'Speaker X:' za kutofautisha wazungumzaji katika mazungumzo.

•inahitajika

Wazungumzaji hukadiriwa kiotomatiki kwa kutumia script au sampuli za sauti zilizotolewa; toa orodha ili kuwabainisha wazi.

Ya kina cfg_scale · seed · enable_safety_checker
chaguomsingi 1.3

Nguvu ya CFG (Classifier-Free Guidance) huamua uzalishaji unavyofuata maandishi kwa karibu, huku ufuataji ukiwa mkubwa zaidi kwenye mipangilio ya juu.

Seed nasibu inayofanya uzalishaji uweze kurudiwa.

POST /run/vibevoice?wait=20 makadirio → $ 0.02
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/vibevoice?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "speakers": [
      {
        "preset": "Frank [EN]"
      },
      {
        "preset": "Carter [EN]"
      }
    ]
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Endesha ombi hili

Key yako inabaki kwenye kivinjari hiki: inatumwa kwa Doitong API pekee na kuhifadhiwa (localStorage) tu ukiweka tiki kwenye Kumbuka. Pata ufunguo wa API

Kuhusu VibeVoice 1.5B

Hubadilisha `script` yenye hadi herufi 90000 kuwa sauti. Mazungumzo yanaweza kutumia viambishi awali vya 'Speaker X:', na orodha ya `speakers` inayohitajika hufafanua sauti. `cfg_scale` huwa kati ya 1 na 2 na hudhibiti ufuataji wa maandishi, na `seed` hufanya uendeshaji uweze kurudiwa. Hurejesha sauti pamoja na muda na kiwango cha sampuli.

Vigezo

JinaAina ChaguomsingiInaruhusiwa Maelezo
scriptinahitajika
Ainastring
≤ herufi 90,000
Script ya ingizo la sauti, yenye lebo za hiari za 'Speaker X:' za kutofautisha wazungumzaji katika mazungumzo.
speakersinahitajika
Ainaobject[]
Wazungumzaji hukadiriwa kiotomatiki kwa kutumia script au sampuli za sauti zilizotolewa; toa orodha ili kuwabainisha wazi.
speakers[].presetsi lazima
Ainaenum
ChaguomsingiAlice [EN]
Alice [EN]Carter [EN]Frank [EN]Mary [EN] (Background Music)Maya [EN]Anchen [ZH] (Background Music)Bowen [ZH]Xinran [ZH]
Preset ya akiba ya sauti kwa mzungumzaji asiye na `audio_url`; kutoa sampuli hiyo ya sauti hutangulia preset.
speakers[].audio_urlsi lazima
Ainaurl · audio
URL ya faili la sampuli ya sauti; kulitoa hubatilisha `preset`.
seedsi lazima
Ainainteger | null
Seed nasibu inayofanya uzalishaji uweze kurudiwa.
cfg_scalesi lazima
Ainanumber
Chaguomsingi1.3
1 – 2
Nguvu ya CFG (Classifier-Free Guidance) huamua uzalishaji unavyofuata maandishi kwa karibu, huku ufuataji ukiwa mkubwa zaidi kwenye mipangilio ya juu.
enable_safety_checkersi lazima
Ainaboolean
Chaguomsingitrue
Ukaguzi unaweza kulegezwa kwa kuweka false, ikiwa mpigaji simu ameidhinishwa.
inahitajika

Tokeo

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "vibevoice",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 20,
    "usd": "0.02",
    "charged": 20,
    "refunded": 0
  },
  "input": {
    "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "speakers": [
      {
        "preset": "Frank [EN]"
      },
      {
        "preset": "Carter [EN]"
      }
    ]
  },
  "output": {
    "audio": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_name": "0-output.mp3",
      "file_size": 1843200
    },
    "duration": 5,
    "sample_rate": 24000,
    "generation_time": 5.6,
    "rtf": 0.53
  },
  "outputs": [
    {
      "type": "audio",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_size": 1843200,
      "duration": 12,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Faili zako, chaguo lakoKila outputs[].url ni nakala kwenye hifadhi yetu: huhifadhiwa milele (hutozwa kwa GB kwa mwezi) au 7 siku bila malipo, kulingana na mpangilio wa akaunti yako au ?storage=.
Muundo uleule kwenye kila modelitype, url, content_type, width, height na duration, kwa picha, video na sauti. output ni kitu cha matokeo cha modeli yenyewe.
Sehemu za tokeo
audio
object {url, content_type, file_name, file_size}Faili la sauti lenye usemi uliosanisishwa.
duration
numberUrefu wa tokeo la sauti, unaopimwa kwa sekunde.
sample_rate
integerKiwango cha sampuli cha tokeo la sauti.
generation_time
numberMuda wa uzalishaji wa sauti, unaopimwa kwa sekunde.
rtf
numberKipengele cha wakati halisi kinachokokotolewa kama generation_time ikigawanywa kwa audio_duration; thamani ndogo huashiria utendaji bora.

Miundo zaidi: Maandishi hadi Matamshi

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/vibevoice.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt