Peke ki ngā ihirangi

Wizper (Whisper v3)

Whakauru

id tauira 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"

Tae atu ki te $ 1.998 mō ia whakahaerenga ka utua mō te whakamahinga tūturu, ka whakahokia te toenga Whakahaerehia ki tēnei whārangi

Tikina he kī API
OpenAI Kōrero ki te Kuputuhi #transcription#speech

He tuhi kōrero reo me te whakamāori ki te reo Pākehā mā Whisper v3, me ngā wāhanga whai tohu wā

OpenAI · Kuputuhi

Kei konei tō hua tuatahi

Hangaia he tono ki raro nei, ka whakahaere mā tō kī API. Ka tāruatia ngā putanga ki tō mātou rokiroki, ka puritia mō ake tonu atu, mō rānei 7 rā mō te kore utu.

Hangaia he tono

Ka hangaia ngā mana whakahaere mai i te aronuinga o te tauira. Ka whakahoungia te waehere me te utu ina whakarerekē koe.

•e hiahiatia ana audio_url
Whakataka he kōnae,

Tāuru tuhi ā-waha kua tukuna hei URL e tohu ana ki tētahi kōnae ororongo kei te hōputu mp3, mp4, mpeg, mpga, m4a, wav, webm rānei.

Arā atu task · language · chunk_level · version · max_segment_len · merge_chunks
task taunoa transcribe

Tūmahi tukatuka ororongo: kōwhiria transcribe, translate rānei.

taunoa en

Kōwhiringa reo ororongo; mā `None` ka tono kitea aunoa, engari ka roa ake te wā whakatau. Mō te tūmahi translate, ko te reo Ingarihi tonu te whāinga whakamāori, nō reira kāore tēnei kōwhiringa reo e whakarerekē i te reo putanga.

taunoa segment

Te taumata taipitopito o ngā wāhanga ka whakahokia.

taunoa 3

Kōwhiringa putanga i roto i te whānau Whisper large; kāore ēnei tauira e whakamahi i tētahi atu momo Whisper.

taunoa 29

Te tepe roa o te wāhanga kōrero, ka inehia ki ngā hēkona, ā, ka wehewehea i muri iho.

POST /run/wizper?wait=20 utu → $ 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"

Whakahaerehia tēnei tono

Ka noho tō kī ki tēnei pūtirotiro: ka tukuna ki te Doitong API anake, ā, ka tiakina ki te localStorage anake ina tohua e koe te Mahara. Tikina he kī API

Mō Wizper (Whisper v3)

Ka tuhi i tētahi kōnae oro mai i tētahi URL (mp3, mp4, mpeg, mpga, m4a, wav, webm rānei), ka whakamāori rānei ki te reo Pākehā mā `task`. Ka tautoko te āpure `language` i ngā uara 99, ā, ka taea te rapunga aunoa. Ka whakahoki i te tuhinga katoa me ngā wāhanga whai tohu wā. Mā `max_segment_len` (10-29 hēkona) me `merge_chunks` e whakahaere te wehewehenga o ngā wāhanga.

Ngā tawhā

Tukuna te ingoa tōmua, te ingoa taketake rānei, kaua e rua. Ngā ingoa tōmua

IngoaMomo TaunoaE whakaaetia ana Whakamārama
audio_urle hiahiatia ana audio
Momourl · audio
Tāuru tuhi ā-waha kua tukuna hei URL e tohu ana ki tētahi kōnae ororongo kei te hōputu mp3, mp4, mpeg, mpga, m4a, wav, webm rānei.
taskkōwhiringa
Momoenum
Taunoatranscribe
transcribetranslate
Tūmahi tukatuka ororongo: kōwhiria transcribe, translate rānei.
languagekōwhiringa
Momoenum
Taunoaen
afamarasazbabebgbnbobrbscacscyda
+83 anōdeeleneseteufafifofrglguhahawhehihrhthuhyidisitjajwkakkkmknkolalblnloltlvmgmimkmlmnmrmsmtmynenlnnnoocpaplpsptrorusasdsiskslsnsosqsrsusvswtatetgthtktltrttukuruzviyiyozh
Kōwhiringa reo ororongo; mā `None` ka tono kitea aunoa, engari ka roa ake te wā whakatau. Mō te tūmahi translate, ko te reo Ingarihi tonu te whāinga whakamāori, nō reira kāore tēnei kōwhiringa reo e whakarerekē i te reo putanga.
chunk_levelkōwhiringa
Momostring
Taunoasegment
Te taumata taipitopito o ngā wāhanga ka whakahokia.
max_segment_lenkōwhiringa
Momointeger
Taunoa29
10 – 29
Te tepe roa o te wāhanga kōrero, ka inehia ki ngā hēkona, ā, ka wehewehea i muri iho.
merge_chunkskōwhiringa
Momoboolean
Taunoatrue
Mana hanumi wāhanga whaiarua; ka whakaaetia te hanumi mēnā kāore te roanga o te wāhanga hua e neke ake i te max_segment_len.
versionkōwhiringa
Momostring
Taunoa3
Kōwhiringa putanga i roto i te whānau Whisper large; kāore ēnei tauira e whakamahi i tētahi atu momo Whisper.
e hiahiatia ana Ingoa tōmua, e whakaaetia ana hoki

Mō ngā tawhā kōnae, whakamahia he URL tūmatanui https://, he URI data: tae atu ki te 10 MB, he file_url rānei o tētahi tukuake. Ngā kōnae

Putanga

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"
  }
}
Ō kōnae, māu e whiriwhiriKo ia url o outputs[] he tārua kei tō mātou rokiroki: ka puritia mō ake tonu atu (ka utua ia GB-marama) mō rānei 7 rā mō te kore utu, e ai ki ngā tautuhinga o tō pūkete, ki te ?storage= rānei.
He ōrite te hanga ki ia tauiratype, url, content_type, width, height me duration, mō ngā pikitia, ataata me te oro. Ko output te ahanoa hua ake o te tauira.
Ngā āpure o te putanga
text
stringHe kupu kua tuhia mai i te ororongo.
chunks
array of object {timestamp, text}Ngā wāhanga ororongo me ngā tohuwā.
languages
array of enum (string)Ngā hua kitenga reo ororongo, ka whakahokia hei rārangi reo i whakapaetia, ko null te uara taunoa.

Mō ngā āpiha AI: kei te wātea tēnei whārangi hei Markdown ki https://doitong.com/mi/developers/models/wizper.md. Ngā tauira me ngā aratohu katoa: https://doitong.com/developers/llms.txt