Ruka hadi kwenye maudhui
Kiswahili
Pata ufunguo wa API

Pipecat's Smart Turn model

Unganisha

Kitambulisho cha modeli smart-turn 
# 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/smart-turn?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"

Hadi $ 1.998 kwa kila uendeshaji hutozwa kulingana na matumizi halisi, yaliyosalia yanarejeshwa Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
Open model Matamshi hadi Maandishi

Utambuzi wa zamu unaotegemea sauti unaotabiri ikiwa zamu ya mzungumzaji imekamilika au haijakamilika

OpenAPI Markdown
Open model · Data (JSON)

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.

•inahitajika audio_url
Dondosha faili, au

URL inayoelekeza kwenye faili la sauti kwa uchakataji.

POST /run/smart-turn?wait=20 makadirio → $ 1.998 
# 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/smart-turn?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 Pipecat's Smart Turn model

Hupokea `audio_url` na kuainisha ikiwa mzungumzaji amemaliza zamu yake. Hurejesha `prediction` (1 ikiwa imekamilika, 0 ikiwa haijakamilika), `probability`, na vipimo vya uelekezaji. Ni muhimu kuamua wakati wakala wa sauti anapaswa kujibu, akitumia sauti moja kwa moja badala ya manukuu.

Vigezo

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

JinaAina ChaguomsingiInaruhusiwa Maelezo
audio_urlinahitajika audio
Ainaurl · audio
URL inayoelekeza kwenye faili la sauti kwa uchakataji.
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": "smart-turn",
  "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": 1998,
    "usd": "1.998",
    "charged": 1998,
    "refunded": 0
  },
  "input": {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "output": {
    "prediction": 1,
    "probability": 1.0,
    "metrics": {}
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "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
prediction
integerUainishaji wa zamu uliotabiriwa: Complete huwakilishwa na 1, na Incomplete na 0.
probability
numberUwezekano uliotolewa kwa uainishaji wa zamu uliotabiriwa.
metrics
objectVipimo vilivyorekodiwa wakati wa inference.
Maandishi
Open model Matamshi hadi Maandishi

Speech-to-Text Tofauti: 3

$ 0.0008 / sekunde ya sauti ya ingizo salio za API 0.8 / sekunde ya sauti ya ingizo
Maandishi
Open model Matamshi hadi Maandishi

Speech-To-text · Stream Tofauti: 3

$ 0.0008 / sekunde ya sauti ya ingizo salio za API 0.8 / sekunde ya sauti ya ingizo
Maandishi
Open model Matamshi hadi Maandishi

Speech-to-Text · Turbo Tofauti: 3

$ 0.0008 / sekunde ya sauti ya ingizo salio za API 0.8 / sekunde ya sauti ya ingizo
Maandishi
Open model Matamshi hadi Maandishi

Speech-to-Text · Turbo · Stream

$ 0.0008 / sekunde ya sauti ya ingizo salio za API 0.8 / sekunde ya sauti ya ingizo

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