Dža ko lil

Wizper (Whisper v3)

Integriruj

Modelosko id wizper
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/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.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Dži $1.998 pe jekh keripe čargeime palal realno labaripen, o aver si irime Phir les kate

Lel API klidin
OpenAI Lav ko Teksto #transcription#speech

Whisper v3 vakeripasko transkript thaj angluno prevod angličanes timestamp-ime chunk-enca

OpenAI · Teksto

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 audio_url
Čhiv jekh fajl, vaj

Inputo e transkripciako savo avol sar URL kaj sikavel audio-fajlo ande mp3, mp4, mpeg, mpga, m4a, wav vaj webm formato.

Lučhe task · language · chunk_level · version · max_segment_len · merge_chunks
task standardno transcribe

Audio-procesosko zadacha: alosar transcribe vaj translate.

standardno en

Alosaripe e audio-chibako, kaj `None` mangel avto­ma­tikano džangipe, numa buter vremi andar lunger inference. Vaś translate, English si sajekh o target e translacijako, numa kadava alosaripe na paruvkerel e rezultatoski chib.

standardno segment

Granulariteto e vratisarde chunkurenqo.

standardno 3

Versiako alosaripe ande bari familija Whisper; kadale modelonendar na utilizinel pes aver Whisper-varijanto.

standardno 29

Limitos e dživipaskere segmentosko, merime ande sekunda, palal savo kerel pes o čhinavipe.

POST /run/wizper?wait=20 hesab → $1.998
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/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.ru/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 Wizper (Whisper v3)

Transkribiril jekh audio fajlo katar o URL (mp3, mp4, mpeg, mpga, m4a, wav vaj webm), vaj amboldel le pe anglikani čhib e `task` parametreca. O `language` fildo podržil 99 valure, thaj o automatikano dikhipen si šajutno. Vratil o cilo teksto thaj kotorora thovde vaktenca. `max_segment_len` (10-29 sekunde) thaj `merge_chunks` kontrolirin sar o kotorora hulaven pe.

Parametra

Bičhalav vaj e kanonikano nav vaj e native nav, na duj. Kanonikane nava

NavTip standardnoMuklo Vakeripe
audio_urltrubul audio
Tipurl · audio
Inputo e transkripciako savo avol sar URL kaj sikavel audio-fajlo ande mp3, mp4, mpeg, mpga, m4a, wav vaj webm formato.
taskopcionalno
Tipenum
standardnotranscribe
transcribetranslate
Audio-procesosko zadacha: alosar transcribe vaj translate.
languageopcionalno
Tipenum
standardnoen
afamarasazbabebgbnbobrbscacscyda
+83 averdeeleneseteufafifofrglguhahawhehihrhthuhyidisitjajwkakkkmknkolalblnloltlvmgmimkmlmnmrmsmtmynenlnnnoocpaplpsptrorusasdsiskslsnsosqsrsusvswtatetgthtktltrttukuruzviyiyozh
Alosaripe e audio-chibako, kaj `None` mangel avto­ma­tikano džangipe, numa buter vremi andar lunger inference. Vaś translate, English si sajekh o target e translacijako, numa kadava alosaripe na paruvkerel e rezultatoski chib.
chunk_levelopcionalno
Tipstring
standardnosegment
Granulariteto e vratisarde chunkurenqo.
max_segment_lenopcionalno
Tipinteger
standardno29
10 – 29
Limitos e dživipaskere segmentosko, merime ande sekunda, palal savo kerel pes o čhinavipe.
merge_chunksopcionalno
Tipboolean
standardnotrue
Kontrolo e jekh-palal-jekheskero chunk-milavipe, savo mukel milavipe numa kana o rezultato segmentosko dživipe na si buter sar max_segment_len.
versionopcionalno
Tipstring
standardno3
Versiako alosaripe ande bari familija Whisper; kadale modelonendar na utilizinel pes aver Whisper-varijanto.
trubul Kanonikano nav, vi akceptime

Fajloske parametra lel jekh publikano https:// URL, jekh data: URI dži 10 MB, vaj e file_url uploadoski. Fajlura

Rezultato

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.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/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
text
stringTeksto transkribime andar o audio.
chunks
array of object {timestamp, text}Audio-chunkura timestampsenca.
languages
array of enum (string)Rezultatura e audio-chibakere džangipnastar, vratisarde sar lista inferred chibenca, null sar standardno vrednosta.

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