Dža ko lil

VibeVoice 7B

Integriruj

Modelosko id vibevoice/7b
# 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/7b?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"

Kava mangipen: ≈$0.04 40 API krediti Phir les kate

Lel API klidin
Microsoft Teksto ko Lav #text-to-speech#multi-speaker#podcast

Majbaro VibeVoice modelo pala dialogo bute vakerutnenca, skriptenca dži ko 30000 karakterja

Microsoft · Audio

Tiro prvo rezultato si kate

Ker tele jekh mangipen thaj phir les tire API klidinosa. E rezultatur si kopirime amare arakhipneste, vično vaj 7 dives bilačhes.

Ker jekh mangipen

O kontrolura kerde si katar e schemaske. O kodo thaj e cena menjinen sar tu len menjines.

•trubul 88 / 30000

Speech inputo script, opcionalno 'Speaker X:' labelenca te distinģuinen le vakerutnen ande dialogo.

•trubul

Vakerutne avri ankalavena avtomatikone scriptosa vaj dine voice sample-nca; den jekh lista te sikaven len eksplicitno.

Lučhe cfg_scale · seed · enable_safety_checker
standardno 1.3

CFG (Classifier-Free Guidance) strength sikavel sar but keripe palal lel o teksto; majbaro settingo del majzoralo adherence.

Random semeno savo kerel e keripe te šaj pale kerel pes.

POST /run/vibevoice/7b?wait=20 hesab → $0.04
# 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/7b?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"

Phandel kava mangipen

Tiro kluč ačhel kadale browsereste: bičhalel pes numa ko Doitong API thaj šuvav pes (localStorage) numa te tiknes Remember. Le jekh API ključ

Palal VibeVoice 7B

Paruvel `script` dži ko 30000 karakterja andro vakeripen, e 'Speaker X:' prefiksenca pala dialogo thaj zorutni `speakers` lista pala glasa. `cfg_scale` džal katar 1 dži ko 2 thaj `seed` del palem kerde rezultato. Si 7B verzija e familijaki, e majcikne tekstoske limitosa sar 1.5B modelo.

Parametra

NavTip standardnoMuklo Vakeripe
scripttrubul
Tipstring
≤ 30,000 simbolura
Speech inputo script, opcionalno 'Speaker X:' labelenca te distinģuinen le vakerutnen ande dialogo.
speakerstrubul
Tipobject[]
Vakerutne avri ankalavena avtomatikone scriptosa vaj dine voice sample-nca; den jekh lista te sikaven len eksplicitno.
speakers[].presetopcionalno
Tipenum
standardnoAlice [EN]
Alice [EN]Carter [EN]Frank [EN]Mary [EN] (Background Music)Maya [EN]Anchen [ZH] (Background Music)Bowen [ZH]Xinran [ZH]
Fallback voice preset vaš vakerutno bi `audio_url`; kana den audio sample, kodo si majzoralo sar preset.
speakers[].audio_urlopcionalno
Tipurl · audio
Voice sample audio fajl URL; kana les den, override-kerel `preset`.
seedopcionalno
Tipinteger | null
Random semeno savo kerel e keripe te šaj pale kerel pes.
cfg_scaleopcionalno
Tipnumber
standardno1.3
1 – 2
CFG (Classifier-Free Guidance) strength sikavel sar but keripe palal lel o teksto; majbaro settingo del majzoralo adherence.
enable_safety_checkeropcionalno
Tipboolean
standardnotrue
Screening šaj te avel relaksirime te postavil pes false, numa kana o manglo si autorizuime.
trubul

Rezultato

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "vibevoice/7b",
  "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": 40,
    "usd": "0.04",
    "charged": 40,
    "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"
  }
}
Tire fajlura, tiro alosaripenSako outputs[].url si kopija amare arakhipneste: vično (čargeime per GB-mase) vaj 7 dives bilačhes, tiro kontoskere regulaciatar vaj ?storage=.
Sa jekh forma sako modeloθartype, url, content_type, width, height thaj duration, varesave imajinake, video thaj audio-ke. output si o modelosko korkoro resultosko objekto.
Outputoske fieldura
audio
object {url, content_type, file_name, file_size}Audio fajlo savo si synthesize-ime vakeresa.
duration
numberDužina e audiosko rezultatoski, merime ande sekunda.
sample_rate
integerSampling rate e audiosko rezultatosko.
generation_time
numberVakti e audioski keripesko, merime ande sekunda.
rtf
numberReal-time factor kalkulirime sar generation_time divided by audio_duration; teleder vrednosti sikaven feder performance.

Bute modeli: Teksto ko Lav

AI agentenge: kadija rig sar Markdown si kate https://doitong.com/rom/developers/models/vibevoice/7b.md. Sa e modelura thaj e gidura: https://doitong.com/developers/llms.txt