Saltar al cuntegna

Personaplex · Realtime

Integrar

ID dal model personaplex/realtime
# 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/personaplex/realtime?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# 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"

Fin a $1,80 per execuziun pajà tenor l'utilisaziun effectiva, il rest vegn restituì Lantschar sin questa pagina

Obtegna ina clav API
NVIDIA Audio #audio-to-audio#realtime#conversational

Endpoint Personaplex marcà sco realtime: audio en, resposta discurrida manada d’ina persunalitad or, cun vuschs predefinidas u clonaziun

NVIDIA · 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.

standard You are a wise and fr...

Prompt textual che definescha la persunalitad da l'AI e il context da la conversaziun.

•obligatori audio_url
Trametta in datoteca u

URL da l'input audio che cuntegna la tschantscha da l'utilisader.

Avanzà voice_audio_url · voice · temperature_audio · temperature_text · top_k_audio · top_k_text · seed · enable_safety_checker
Trametta in datoteca u

URL d'in exempel per il voice cloning; ina tschantscha clera da durada d'almain 10 secundas è recumandada. L'exempel vegn clonà immediatamain e remplazza la 'voice' predefinida per la resposta da l'AI.

standard NATF2

ID da la vusch da la resposta da l'AI, surpost da voice_audio_url sch'el vegn furnì. Ses codes differenzieschan natirala (NAT) da varietad (VAR) e feminina (F) da masculina (M).

standard 0.8

Temperatura utilisada durant il sampling da l'audio; augmentar ella producescha resultats pli variads.

standard 0.7

Temperatura utilisada durant il sampling dal text; augmentar ella producescha resultats pli variads.

standard 250

Configuraziun Top-K utilisada per il sampling da tokens d'audio.

standard 25

Configuraziun Top-K utilisada per il sampling da tokens da text.

Seed che controlla la casualitad per resultats reproducibels.

POST /run/personaplex/realtime?wait=20 calculaziun → $1,80
# 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/personaplex/realtime?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# 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 Personaplex · Realtime

Accepta la lingua da l’utilisader via `audio_url` e returna ina resposta discurrida, sia durada, il seed e ina transcripziun da text. La persunalitad vegn da `prompt`, entant che la vusch vegn d’in ID `voice` predefinì u da `voice_audio_url` per clonaziun; almain 10 secundas da lingua clera vegnan recumandadas. Controllas da temperature e top-k existan per il sampling audio e da text.

Parameters

Invia u il num canonic u il num nativ, betg omaduas. Nums canonics

NumTip StandardPermess Descripziun
promptopziunal
Tipstring
StandardYou are a wise and friendly teacher. Answer questions or provide advice in a clear and engaging way.
Prompt textual che definescha la persunalitad da l'AI e il context da la conversaziun.
voiceopziunal
Tipenum
StandardNATF2
NATF0NATF1NATF2NATF3NATM0NATM1NATM2NATM3VARF0VARF1VARF2VARF3VARF4VARM0VARM1VARM2
+2 dapliVARM3VARM4
ID da la vusch da la resposta da l'AI, surpost da voice_audio_url sch'el vegn furnì. Ses codes differenzieschan natirala (NAT) da varietad (VAR) e feminina (F) da masculina (M).
voice_audio_urlopziunal
Tipurl · audio
URL d'in exempel per il voice cloning; ina tschantscha clera da durada d'almain 10 secundas è recumandada. L'exempel vegn clonà immediatamain e remplazza la 'voice' predefinida per la resposta da l'AI.
temperature_audioopziunal
Tipnumber
Standard0.8
0 – 2
Temperatura utilisada durant il sampling da l'audio; augmentar ella producescha resultats pli variads.
temperature_textopziunal
Tipnumber
Standard0.7
0 – 2
Temperatura utilisada durant il sampling dal text; augmentar ella producescha resultats pli variads.
top_k_audioopziunal
Tipinteger
Standard250
1 – 2 048
Configuraziun Top-K utilisada per il sampling da tokens d'audio.
top_k_textopziunal
Tipinteger
Standard25
1 – 1 000
Configuraziun Top-K utilisada per il sampling da tokens da text.
seedopziunal
Tipinteger | null
Seed che controlla la casualitad per resultats reproducibels.
audio_urlobligatori audio
Tipurl · audio
URL da l'input audio che cuntegna la tschantscha da l'utilisader.
enable_safety_checkeropziunal
Tipboolean
Standardtrue
La controlla po vegnir schluccada cun definir false, premess che l'appelant saja autorisà.
obligatori Num canonic, er acceptà

Ils parameters da datotecas acceptan ina URL publica https://, ina URI data: fin a 10 MB u il file_url d'ina chargiada. Datotecas

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "personaplex/realtime",
  "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": 1800,
    "usd": "1.80",
    "charged": 1800,
    "refunded": 0
  },
  "input": {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "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
    },
    "text": " Thank you for calling SwiftPlex Appliances. This is Farhod, how can I help you today? I understand your concern. The replacement part is out of stock, so we can't ship it right away. We can use an alternative part that will arrive in 3 days. Would you like to proceed with that?",
    "duration": 5,
    "seed": 42
  },
  "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}Audio da resposta generà da l'AI en format WAV cun 24 kHz.
text
stringTranscripziun textuala da la resposta da l'AI.
duration
numberLunghezza da l'audio generà, mesirada en secundas.
seed
integerValur da seed applitgada durant la generaziun.

Dapli models: Audio

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