Njuolgga sisdollui

Wizper (Whisper v3)

Integrere

Modealla-id wizper
# 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/wizper?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"

Gitta 1,998 $ juohke ráŋggas mákso duohta geavaheami mielde, loahppa máhcaheami Vuodje dán siiddu alde

Oza API-čoavdaga
OpenAI Hállamis teaksta #transcription#speech

Whisper v3-jiettačállin ja jorgaleapmi eŋgelasgillii áigegaskkaiguin merkejuvvon oasiiguin

OpenAI · Teaksta

Dát lea du vuosttaš bohtos

Daga jearaldaga vuolábealde ja vuodje dan iežat API-čoavddain. Boađusat kopierejuvvojit min vurkemii, bisuhuvvojit álo dahje 7 beaivvi nuvttá.

Ráhkat jearaldaga

Kontrollat ráhkaduvvojit modealla skeama vuođul. Koda ja haddi ođasmahttojuvvojit go rievddadat daid.

•gáibiduvvo audio_url
Luoitte fiilla, dahje

Čállingeđgen-sisa-addi, biddjon URL:n mii čájeha jietnafiilii mp3, mp4, mpeg, mpga, m4a, wav dahje webm formáhtas.

Viiddiduvvon task · language · chunk_level · version · max_segment_len · merge_chunks
task standárda transcribe

Jietna-bargu: vállje transcribe dahje translate.

standárda en

Jiena giellaválljen, gos `None` bivdá automáhtalaš gávdnama guhkit inference-áiggi ovddas. Translate-barggus lea eŋgelasgiella álo jorgaleami ulbmil, nu ahte dát giellaválljen ii rievdat boađusgiella.

standárda segment

Vástiduvvon čuokkisráhkadusa dárkilvuohta.

standárda 3

Veršuvnna válljen Whisper large-bearažis; eará Whisper-varianttaid dát modeallat eai geavat.

standárda 29

Huma-segmentta guhkkodatrájádus, sekunddain mihtiduvvon, man maŋŋá juohkin dáhpáhuvvá.

POST /run/wizper?wait=20 haddemearrádus → 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/wizper?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"

Geavat dán ohcamuša

Du key báhcá dán fierpmádatlogan: dat sáddejuvvo dušše Doitong API:ii ja vurkejuvvo (localStorage) dušše jos válljet Remember. Viečča API-keya

Dát lea Wizper (Whisper v3) birra

Čállá jietnafiilla URL:as (mp3, mp4, mpeg, mpga, m4a, wav dahje webm), dahje jorgala dan eŋgelasgillii `task` bokte. `language`-gieddi doarju 99 árvvu, ja automáhtalaš giela dovdan lea vejolaš. Máhcaha olles teavstta ja áigegaskkaiguin merkejuvvon osiid. `max_segment_len` (10-29 sekundda) ja `merge_chunks` stivrejit mo oasit juhkkojit.

Parametterat

Sádde kanonala nama dahje iežas nama, ii goappašiid. Kanonala namat

NammaŠládja StandárdaDohkkehuvvon Govvádus
audio_urlgáibiduvvo audio
Šládjaurl · audio
Čállingeđgen-sisa-addi, biddjon URL:n mii čájeha jietnafiilii mp3, mp4, mpeg, mpga, m4a, wav dahje webm formáhtas.
taskeaktodáhtolaš
Šládjaenum
Standárdatranscribe
transcribetranslate
Jietna-bargu: vállje transcribe dahje translate.
languageeaktodáhtolaš
Šládjaenum
Standárdaen
afamarasazbabebgbnbobrbscacscyda
+83 eanetdeeleneseteufafifofrglguhahawhehihrhthuhyidisitjajwkakkkmknkolalblnloltlvmgmimkmlmnmrmsmtmynenlnnnoocpaplpsptrorusasdsiskslsnsosqsrsusvswtatetgthtktltrttukuruzviyiyozh
Jiena giellaválljen, gos `None` bivdá automáhtalaš gávdnama guhkit inference-áiggi ovddas. Translate-barggus lea eŋgelasgiella álo jorgaleami ulbmil, nu ahte dát giellaválljen ii rievdat boađusgiella.
chunk_leveleaktodáhtolaš
Šládjastring
Standárdasegment
Vástiduvvon čuokkisráhkadusa dárkilvuohta.
max_segment_leneaktodáhtolaš
Šládjainteger
Standárda29
10 – 29
Huma-segmentta guhkkodatrájádus, sekunddain mihtiduvvon, man maŋŋá juohkin dáhpáhuvvá.
merge_chunkseaktodáhtolaš
Šládjaboolean
Standárdatrue
Lagaš čuokkisráhkadusaid ovttastahttin, mas ovttastahttin lea lobálaš dušše dalle go boahttevaš segmentta guhkkodat ii leat stuorát go max_segment_len.
versioneaktodáhtolaš
Šládjastring
Standárda3
Veršuvnna válljen Whisper large-bearažis; eará Whisper-varianttaid dát modeallat eai geavat.
gáibiduvvo Kanonala namma, maid sáhttá geavahit

Fiilaparametterat váldet almmolaš https:// URL:a, data: URI:a gitta 10 MB, dahje uploada file_url:a. Fiillat

Boađus

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "wizper",
  "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": {
    "text": "string",
    "chunks": [
      {
        "timestamp": [],
        "text": "string"
      }
    ],
    "languages": [
      "af"
    ]
  },
  "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"
  }
}
Du fiillat, du válljenJuohke outputs[].url lea kopia min vurkemis: bisuhuvvo álo (mákso GB-mánu mielde) dahje 7 beaivvi nuvttá, du konto­o heiveheami dahje ?storage= mielde.
Seammá hápmi juohke modeallastype, url, content_type, width, height ja duration, govvii, videoii ja jienai seammá ládje. output lea modealla iežas boađusobjekta.
Outputa giettit
text
stringJienas čállojuvvon teaksta.
chunks
array of object {timestamp, text}Jietna-čuokkisráhkadusat áiggi-diehtuin.
languages
array of enum (string)Jiena giellagávdnama boađusat, máŋggahat gávnnahuvvon gielaid listun, null standárdan.

AI-agenttaide: dán siidu Markdowna lea dáppe https://doitong.com/se/developers/models/wizper.md. Buot modeallat ja ráđit: https://doitong.com/developers/llms.txt