Saltar al cuntegna

VibeVoice 1.5B

Integrar

ID dal model 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"

Questa dumonda: ≈$0,02 20 credits API Lantschar sin questa pagina

Obtegna ina clav API
Microsoft Text a discurrer #text-to-speech#multi-speaker#podcast

Text-to-speech per pliras vuschs e scripts lungs sco podcasts, cun vuschs per mintga pledader

Microsoft · Audio

Tes emprim resultat vegn qua

Construis ina dumonda sutvart e l'exequescha cun tia clav API. Outputs vegnan copiads en nossa memorisaziun, conservads per adina u 7 dis gratuitamain.

Construir ina dumonda

Ils controls vegnan generads dal schema dal model. Il code e ​​il pretsch s'actualiseschan durant che ti als midas.

•obligatori 88 / 90000

Script da l'input da pled, cun etichettas facultativas 'Speaker X:' per differenziar ils pledaders en in dialog.

•obligatori

Ils pledaders vegnan deducids automaticamain cun il script u cun samples da vusch furnids; furnescha ina glista per als specifitgar explicitamain.

Avanzà cfg_scale · seed · enable_safety_checker
standard 1.3

La fermezza CFG (Classifier-Free Guidance) determinescha quant stretg che la generaziun suonda il text; settings pli auts dattan ina aderenza pli gronda.

Semenza casuala che renda la generaziun reproducibla.

POST /run/vibevoice?wait=20 calculaziun → $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"

Executar questa dumonda

Tia clav resta en quest browser: ella vegn tramessa mo al Doitong API e memorisada (localStorage) mo sch'ella scheccas Tiar a memoria. Obtegnair ina clav API

Davart VibeVoice 1.5B

Convertescha in `script` da maximalmain 90000 caracters en pled. Il dialog po utilisar prefixes 'Speaker X:', e la glista `speakers` necessaria definescha las vuschs. `cfg_scale` tanscha da 1 fin 2 e controllescha l'aderenza al text, e `seed` renda las execuziuns reproduciblas. Returna audio plus durada e rata da sampling.

Parameters

NumTip StandardPermess Descripziun
scriptobligatori
Tipstring
≤ 90 000 caracters
Script da l'input da pled, cun etichettas facultativas 'Speaker X:' per differenziar ils pledaders en in dialog.
speakersobligatori
Tipobject[]
Ils pledaders vegnan deducids automaticamain cun il script u cun samples da vusch furnids; furnescha ina glista per als specifitgar explicitamain.
speakers[].presetopziunal
Tipenum
StandardAlice [EN]
Alice [EN]Carter [EN]Frank [EN]Mary [EN] (Background Music)Maya [EN]Anchen [ZH] (Background Music)Bowen [ZH]Xinran [ZH]
Preset da vusch alternativ per in pledader senza `audio_url`; sch'il sample audio vegn furnì, ha el precedenza sur il preset.
speakers[].audio_urlopziunal
Tipurl · audio
URL da la datoteca audio dal sample da vusch; sch'ella vegn furnida, remplazza `preset`.
seedopziunal
Tipinteger | null
Semenza casuala che renda la generaziun reproducibla.
cfg_scaleopziunal
Tipnumber
Standard1.3
1 – 2
La fermezza CFG (Classifier-Free Guidance) determinescha quant stretg che la generaziun suonda il text; settings pli auts dattan ina aderenza pli gronda.
enable_safety_checkeropziunal
Tipboolean
Standardtrue
La controlla po vegnir schluccada cun definir false, premess che l'appelant saja autorisà.
obligatori

Output

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"
  }
}
Tias datotecas, tia decisiunMintga outputs[].url è ina copia en nossa memorisaziun: conservada per adina (pajà per GB-mes) u 7 dis gratuitamain, tenor la configuraziun dal conto u ?storage=.
La medema structura per mintga modeltype, url, content_type, width, height e duration, tant per maletgs sco per video e audio. output è l'object da resultat dal model sez.
Champs da l'output
audio
object {url, content_type, file_name, file_size}Datoteca audio che cuntegna il pled sintetisà.
duration
numberLunghezza da l'output audio, mesirada en secundas.
sample_rate
integerFrequenza da sampling da l'output audio.
generation_time
numberTemp da generaziun da l'audio, mesirà en secundas.
rtf
numberFactur en temp real calculà sco generation_time dividì tras audio_duration; valurs pli pitschnas inditgan ina meglra prestaziun.

Dapli models: Text a discurrer

Per agents AI: questa pagina sco Markdown è disponibla sut https://doitong.com/rm/developers/models/vibevoice.md. Tut ils models e las guidas: https://doitong.com/developers/llms.txt