Ruka hadi kwenye maudhui

Personaplex

Unganisha

Kitambulisho cha modeli personaplex
# 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?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"

Faili kama mfano: $ 0.01 salio za API 10 faili zako hupimwa kabla ya kuendesha Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
NVIDIA Sauti #audio

Modeli ya mazungumzo ya speech-to-speech inayojibu sauti ya usemi kwa persona na sauti unayochagua

NVIDIA · Sauti

Tokeo lako la kwanza linaonekana hapa

Unda ombi hapa chini na uliendeshe kwa ufunguo wako wa API. Matokeo yanakiliwa kwenye hifadhi yetu, yakihifadhiwa milele au 7 siku bila malipo.

Unda ombi

Vidhibiti vinazalishwa kutoka kwenye schema ya modeli. Msimbo na bei husasishwa unapovibadilisha.

chaguomsingi You are a wise and fr...

Kidokezo cha maandishi kinachofafanua persona ya AI na muktadha wa mazungumzo.

Dondosha faili, au

URL ya sampuli ya kunakili sauti; hotuba iliyo wazi ya angalau sekunde 10 inapendekezwa. Sampuli hunakiliwa papo hapo, ikibadilisha 'voice' iliyowekwa awali kwa jibu la AI.

•inahitajika audio_url
Dondosha faili, au

URL ya ingizo la sauti iliyo na hotuba ya mtumiaji.

Ya kina voice · temperature_audio · temperature_text · top_k_audio · top_k_text · seed · enable_safety_checker
chaguomsingi NATF2

Kitambulisho cha sauti ya jibu la AI, kinachobadilishwa na voice_audio_url ikitolewa. Misimbo yake hutofautisha asilia (NAT) na anuwai (VAR), na ya kike (F) na ya kiume (M).

chaguomsingi 0.8

Temperature inayotumika wakati wa kusampuli sauti; kuiongeza hutoa matokeo yenye anuwai zaidi.

chaguomsingi 0.7

Temperature inayotumika wakati wa kusampuli maandishi; kuiongeza hutoa matokeo yenye anuwai zaidi.

chaguomsingi 250

Mpangilio wa Top-K unaotumika kusampuli tokeni za sauti.

chaguomsingi 25

Mpangilio wa Top-K unaotumika kusampuli tokeni za maandishi.

Seed inayodhibiti ubahatishaji kwa matokeo yanayoweza kurudiwa.

POST /run/personaplex?wait=20 makadirio → $ 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/personaplex?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"

Endesha ombi hili

Key yako inabaki kwenye kivinjari hiki: inatumwa kwa Doitong API pekee na kuhifadhiwa (localStorage) tu ukiweka tiki kwenye Kumbuka. Pata ufunguo wa API

Kuhusu Personaplex

Hupokea usemi wa mtumiaji kupitia `audio_url` na kujibu kwa usemi uliotengenezwa, unaorudishwa pamoja na manukuu ya jibu na muda wake. `prompt` ya maandishi hufafanua persona, na `voice` huchagua sauti iliyowekwa tayari. Vinginevyo `voice_audio_url` hunakili sauti kutoka sampuli, ambapo sekunde 10 au zaidi za usemi safi zinapendekezwa. Sampuli inaweza kurekebishwa kupitia mipangilio ya temperature na top-k.

Vigezo

Tuma jina rasmi au jina asilia, si yote mawili. Majina rasmi

JinaAina ChaguomsingiInaruhusiwa Maelezo
promptsi lazima
Ainastring
ChaguomsingiYou are a wise and friendly teacher. Answer questions or provide advice in a clear and engaging way.
Kidokezo cha maandishi kinachofafanua persona ya AI na muktadha wa mazungumzo.
voicesi lazima
Ainaenum
ChaguomsingiNATF2
NATF0NATF1NATF2NATF3NATM0NATM1NATM2NATM3VARF0VARF1VARF2VARF3VARF4VARM0VARM1VARM2
+2 zaidiVARM3VARM4
Kitambulisho cha sauti ya jibu la AI, kinachobadilishwa na voice_audio_url ikitolewa. Misimbo yake hutofautisha asilia (NAT) na anuwai (VAR), na ya kike (F) na ya kiume (M).
voice_audio_urlsi lazima
Ainaurl · audio
URL ya sampuli ya kunakili sauti; hotuba iliyo wazi ya angalau sekunde 10 inapendekezwa. Sampuli hunakiliwa papo hapo, ikibadilisha 'voice' iliyowekwa awali kwa jibu la AI.
temperature_audiosi lazima
Ainanumber
Chaguomsingi0.8
0 – 2
Temperature inayotumika wakati wa kusampuli sauti; kuiongeza hutoa matokeo yenye anuwai zaidi.
temperature_textsi lazima
Ainanumber
Chaguomsingi0.7
0 – 2
Temperature inayotumika wakati wa kusampuli maandishi; kuiongeza hutoa matokeo yenye anuwai zaidi.
top_k_audiosi lazima
Ainainteger
Chaguomsingi250
1 – 2,048
Mpangilio wa Top-K unaotumika kusampuli tokeni za sauti.
top_k_textsi lazima
Ainainteger
Chaguomsingi25
1 – 1,000
Mpangilio wa Top-K unaotumika kusampuli tokeni za maandishi.
seedsi lazima
Ainainteger | null
Seed inayodhibiti ubahatishaji kwa matokeo yanayoweza kurudiwa.
audio_urlinahitajika audio
Ainaurl · audio
URL ya ingizo la sauti iliyo na hotuba ya mtumiaji.
enable_safety_checkersi lazima
Ainaboolean
Chaguomsingitrue
Ukaguzi unaweza kulegezwa kwa kuweka false, ikiwa mpigaji simu ameidhinishwa.
inahitajika Jina rasmi, pia linakubalika

Vigezo vya faili vinakubali URL ya umma ya https://, data: URI ya hadi 10 MB, au file_url ya upakiaji. Faili

Tokeo

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "personaplex",
  "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": {
    "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"
  }
}
Faili zako, chaguo lakoKila outputs[].url ni nakala kwenye hifadhi yetu: huhifadhiwa milele (hutozwa kwa GB kwa mwezi) au 7 siku bila malipo, kulingana na mpangilio wa akaunti yako au ?storage=.
Muundo uleule kwenye kila modelitype, url, content_type, width, height na duration, kwa picha, video na sauti. output ni kitu cha matokeo cha modeli yenyewe.
Sehemu za tokeo
audio
object {url, content_type, file_name, file_size}Sauti ya jibu inayozalishwa na AI katika muundo wa WAV kwa 24 kHz.
text
stringUnukuzi wa maandishi wa jibu kutoka kwa AI.
duration
numberUrefu wa sauti inayozalishwa, unaopimwa kwa sekunde.
seed
integerThamani ya seed inayotumika wakati wa uzalishaji.

Miundo zaidi: Sauti

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/personaplex.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt