Leum chun t-susbaint

Vibevoice

Amalaich

ID a’ mhodail vibevoice/0.5b
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/vibevoice/0.5b?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",
    "speaker": "Frank"
  }'

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

An t-iarrtas seo: ≈$0.01 10 creideasan API Ruith e air an duilleig seo

Faigh iuchair API
Microsoft Teacsa gu Òraid #vibevoice#fast

Teacsa-gu-cainnt aotrom le aon ghuth agus sia guthan ainmichte airson sgriobtaichean fada

Microsoft · Fuaim

Thèid a’ chiad toradh agad an-seo

Tog iarrtas gu h-ìosal agus ruith e leis an iuchair API agad. Tha na h-às-churan air an lethbhreacadh dhan stòradh againn, air an cumail gu bràth no 7 latha an-asgaidh.

Tog iarrtas

Tha na smachdan air an cruthachadh bho sgeama a’ mhodail. Bidh an còd agus a’ phrìs ag ùrachadh fhad ’s a dh’atharraicheas tu iad.

•riatanach 88 / 90000

Sgriobt a thèid a chleachdadh airson co-shìnteachadh cainnte.

speaker •riatanach

Guth a thèid a chleachdadh airson a’ chainnt a lìbhrigeadh.

Adhartach cfg_scale · seed · enable_safety_checker
bun-roghainn 1.3

Tha neart CFG (Classifier-Free Guidance) a’ dearbhadh dè cho dlùth ’s a leanas an gineadh an teacsa, le cumail nas teinne aig roghainnean nas àirde.

Sìol air thuaiream a nì an gineadh ath-riochdachadh.

POST /run/vibevoice/0.5b?wait=20 tuairmse → $0.01
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/vibevoice/0.5b?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",
    "speaker": "Frank"
  }'

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

Ruith an t-iarrtas seo

Fuirichidh an iuchair agad sa bhrobhsair seo: thèid a cur chun Doitong API a-mhàin agus a sàbhaladh (localStorage) a-mhàin ma chuireas tu comharra ri Cuimhnich. Faigh iuchair API

Mu Vibevoice

Leughaidh e `script` de suas ri 90000 caractar ann an aon ghuth air a thaghadh le `speaker`: Frank, Wayne, Carter, Emma, Grace no Mike. Tha `cfg_scale` (1 gu 2) agus `seed` rim faighinn airson gleusadh agus ath-riochdachadh. Làimhsichidh e aon neach-labhairt aig an aon àm, eu-coltach ris na tionndaidhean ioma-labhairt.

Paramadairean

AinmSeòrsa Bun-roghainnCeadaichte Tuairisgeul
scriptriatanach
Seòrsastring
≤ 90,000 caractar
Sgriobt a thèid a chleachdadh airson co-shìnteachadh cainnte.
speakerriatanach
Seòrsaenum
FrankWayneCarterEmmaGraceMike
Guth a thèid a chleachdadh airson a’ chainnt a lìbhrigeadh.
seedroghainneil
Seòrsainteger | null
Sìol air thuaiream a nì an gineadh ath-riochdachadh.
cfg_scaleroghainneil
Seòrsanumber
Bun-roghainn1.3
1 – 2
Tha neart CFG (Classifier-Free Guidance) a’ dearbhadh dè cho dlùth ’s a leanas an gineadh an teacsa, le cumail nas teinne aig roghainnean nas àirde.
enable_safety_checkerroghainneil
Seòrsaboolean
Bun-roghainntrue
Faodar sgrìonadh a shocrachadh le false, ma tha cead aig an neach-gairm.
riatanach

Toradh

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "vibevoice/0.5b",
  "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": 10,
    "usd": "0.01",
    "charged": 10,
    "refunded": 0
  },
  "input": {
    "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "speaker": "Frank"
  },
  "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.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Na faidhlichean agad, do roghainnTha gach outputs[].url na lethbhreac air an stòradh againn: air a chumail gu bràth (air a phàigheadh gach GB-mìos) no 7 latha an-asgaidh, a rèir suidheachadh a’ chunntais agad no ?storage=.
An aon chruth air gach modailtype, url, content_type, width, height agus duration, airson dealbhan, bhidio agus fuaim le chèile. ’S e output nì toraidh a’ mhodail fhèin.
Raointean toraidh
audio
object {url, content_type, file_name, file_size}Faidhle claisneachd anns a bheil a’ chainnt cho-shintte.
duration
numberFad an às-chuir claisneachd, air a thomhas ann an diogan.
sample_rate
integerÌre-samplachaidh an às-chuir claisneachd.
generation_time
numberÙine gineadh claisneachd, air a thomhas ann an diogan.
rtf
numberFactar fìor-ùine air a thomhas mar generation_time air a roinn le audio_duration; tha luachan nas lugha a’ comharrachadh coileanadh nas fheàrr.

Barrachd mhodalan: Teacsa gu Òraid

Do riochdairean AI: tha an duilleag seo mar Markdown aig https://doitong.com/gd/developers/models/vibevoice/0.5b.md. Na modailean agus na treòraichean uile: https://doitong.com/developers/llms.txt