Njuolgga sisdollui

VibeVoice 1.5B

Integrere

Modealla-id vibevoice
# 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?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.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Dát ohcamuš: ≈0,02 $ 20 API-kreditta Vuodje dán siiddu alde

Oza API-čoavdaga
Microsoft Teavsttas hállan #text-to-speech#multi-speaker#podcast

Máŋggahupmi tekstas-jietnagillii guhkes skripttaid várás nugo podcastat, sierra jienaiguin juohke hupmái

Microsoft · Jietna

Dát lea du vuosttaš bohtos

Daga jearaldaga vuolábealde ja vuodje dan iežat API-čoavddain. Boađusat kopierejuvvojit min vurkemii, bisuhuvvojit álo dahje 7 beaivvi nuvttá.

Ráhkat jearaldaga

Kontrollat ráhkaduvvojit modealla skeama vuođul. Koda ja haddi ođasmahttojuvvojit go rievddadat daid.

•gáibiduvvo 88 / 90000

Hupmansisa-addi teaksta, mas sáhttet leat eaktodáhtolaš 'Speaker X:' merkamat earuheamen ságastallama hupmiid.

•gáibiduvvo

Hupmit meroštallojuvvojit automáhtalaččat teavstta dahje addojuvvon jietnaovdamearkkaid vuođul; atte listtu meroštallat sin njuolga.

Viiddiduvvon cfg_scale · seed · enable_safety_checker
standárda 1.3

CFG (Classifier-Free Guidance) nanusvuohta mearrida, man dárkilit ráhkadeapmi čuovvu teavstta; alit árvvut čuvvot dárkileappot.

Ozanlaš seedárdna, mii dahká ráhkadeami geardduhahttin.

POST /run/vibevoice?wait=20 haddemearrádus → 0,02 $
# 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?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.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Geavat dán ohcamuša

Du key báhcá dán fierpmádatlogan: dat sáddejuvvo dušše Doitong API:ii ja vurkejuvvo (localStorage) dušše jos válljet Remember. Viečča API-keya

Dát lea VibeVoice 1.5B birra

Rievdada gitta 90000 teavstta `script`-a jietnagillii. Dialoga sáhttá geavahit 'Speaker X:'-álggahusaid, ja dárbbašlaš `speakers`-listu mearrida jienaid. `cfg_scale` lea 1 rájes 2 rádjái ja stivre tekstii čuovvuma, ja `seed` dahká geavahusaid geardduhahttin. Máhccaha audioa, guhkkodaga ja sample rate:a.

Parametterat

NammaŠládja StandárdaDohkkehuvvon Govvádus
scriptgáibiduvvo
Šládjastring
≤ 90 000 mearkka
Hupmansisa-addi teaksta, mas sáhttet leat eaktodáhtolaš 'Speaker X:' merkamat earuheamen ságastallama hupmiid.
speakersgáibiduvvo
Šládjaobject[]
Hupmit meroštallojuvvojit automáhtalaččat teavstta dahje addojuvvon jietnaovdamearkkaid vuođul; atte listtu meroštallat sin njuolga.
speakers[].preseteaktodáhtolaš
Šládjaenum
StandárdaAlice [EN]
Alice [EN]Carter [EN]Frank [EN]Mary [EN] (Background Music)Maya [EN]Anchen [ZH] (Background Music)Bowen [ZH]Xinran [ZH]
Várrejiena ovdagihtiiásahus hupmái geas ii leat `audio_url`; addojuvvon jietnaovdamearka manná ovdagihtiiásahusa ovddabeallái.
speakers[].audio_urleaktodáhtolaš
Šládjaurl · audio
Jietnaovdamearkka jietnafiilla URL; dan addin buhttá `preset`.
seedeaktodáhtolaš
Šládjainteger | null
Ozanlaš seedárdna, mii dahká ráhkadeami geardduhahttin.
cfg_scaleeaktodáhtolaš
Šládjanumber
Standárda1.3
1 – 2
CFG (Classifier-Free Guidance) nanusvuohta mearrida, man dárkilit ráhkadeapmi čuovvu teavstta; alit árvvut čuvvot dárkileappot.
enable_safety_checkereaktodáhtolaš
Šládjaboolean
Standárdatrue
Gáhtten sáhttá loahpahuvvot bidjamiin false, jos geavaheaddji lea das ovttastuvvon.
gáibiduvvo

Boađus

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.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Du fiillat, du válljenJuohke outputs[].url lea kopia min vurkemis: bisuhuvvo álo (mákso GB-mánu mielde) dahje 7 beaivvi nuvttá, du konto­o heiveheami dahje ?storage= mielde.
Seammá hápmi juohke modeallastype, url, content_type, width, height ja duration, govvii, videoii ja jienai seammá ládje. output lea modealla iežas boađusobjekta.
Outputa giettit
audio
object {url, content_type, file_name, file_size}Jietnafiila mii sisttisdoallá syntetiserejuvvon hupmama.
duration
numberJiena boađusa guhkkodat, sekundain mihtiduvvon.
sample_rate
integerJiena boađusa sampalašuvnnaleaktu.
generation_time
numberJiena ráhkadeami áigi, sekundain mihtiduvvon.
rtf
numberReálaáigefaktor rehkenastojuvvon generation_time/audio_duration; unnit árvvut čájehit buoret beavttu.

Eanet modeallat: Teavsttas hállan

AI-agenttaide: dán siidu Markdowna lea dáppe https://doitong.com/se/developers/models/vibevoice.md. Buot modeallat ja ráđit: https://doitong.com/developers/llms.txt