Ruka hadi kwenye maudhui

MiniMax Speech-02 HD

Unganisha

Kitambulisho cha modeli minimax/speech-02-hd
# 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/minimax/speech-02-hd?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello from Doitong. This is a short test sentence."
  }'

# 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"

Ombi hili: $ 0.005 salio za API 5 Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
MiniMax · 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.

•inahitajika 50 / 5000

Maandishi ya ingizo la usemi, yenye kikomo cha vibambo 5000 na yanayohitaji angalau kibambo 1 kisicho nafasi nyeupe.

Ya kina output_format · language_boost · enable_safety_checker · voice_setting · audio_setting · pronunciation_dict
output_format chaguomsingi hex

Umbizo la maudhui ya tokeo; hutumika tu kwa majibu yasiyotiririshwa.

Huboresha utambuzi kwa lugha na lahaja zilizochaguliwa.

chaguomsingi {"english_normalizati...

Mipangilio ya kusanidi sauti.

Mipangilio ya kusanidi sauti.

Kamusi maalum ya matamshi inayotumika kubadilisha maandishi.

POST /run/minimax/speech-02-hd?wait=20 makadirio → $ 0.005
# 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/minimax/speech-02-hd?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello from Doitong. This is a short test sentence."
  }'

# 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 MiniMax Speech-02 HD

Huzalisha sauti kutoka hadi herufi 5000 za `text` kwa kutumia toleo la ubora wa HD la Speech-02. Unaweza kurekebisha sauti kupitia `voice_setting`, kuweka `audio_setting`, kutumia `pronunciation_dict`, na kuchagua `language_boost` kati ya chaguo 38. `output_format` inaweza kuwa url au hex. Matokeo yana faili la sauti na urefu wake kwa milisekunde.

Vigezo

JinaAina ChaguomsingiInaruhusiwa Maelezo
enable_safety_checkersi lazima
Ainaboolean
Chaguomsingitrue
Ukaguzi unaweza kulegezwa kwa kuweka false, ikiwa mpigaji simu ameidhinishwa.
textinahitajika
Ainastring
≤ herufi 5,000
Maandishi ya ingizo la usemi, yenye kikomo cha vibambo 5000 na yanayohitaji angalau kibambo 1 kisicho nafasi nyeupe.
voice_settingsi lazima
Ainaobject
Chaguomsingi{"english_normalization":false,"pitch":0,"speed":1,"voice_id":"Wise_Woman","vol":1}
Mipangilio ya kusanidi sauti.
voice_setting.voice_idsi lazima
Ainastring
ChaguomsingiWise_Woman
≥ 1 characters
Kitambulisho cha sauti kilichobainishwa awali kinachotumika kwa usanisi wa usemi.
voice_setting.speedsi lazima
Ainanumber
Chaguomsingi1
0.5 – 2
Kasi ya kuzungumza, kuanzia 0.5 hadi 2.0.
voice_setting.volsi lazima
Ainanumber
Chaguomsingi1
0.01 – 10
Sauti ya tokeo, kuanzia 0 hadi 10.
voice_setting.pitchsi lazima
Ainainteger
Chaguomsingi0
-12 – 12
Pitch ya sauti, kuanzia -12 hadi 12.
voice_setting.emotionsi lazima
Ainaenum
happysadangryfearfuldisgustedsurprisedneutral
Toni ya kihisia ya usemi uliosanisishwa.
voice_setting.english_normalizationsi lazima
Ainaboolean
Chaguomsingifalse
Chaguo la kusanifisha maandishi ya Kiingereza linalobadilisha kiasi kidogo cha ucheleweshaji wa ziada kwa usomaji bora wa nambari.
audio_settingsi lazima
Ainaobject
Mipangilio ya kusanidi sauti.
audio_setting.sample_ratesi lazima
Ainaenum
Chaguomsingi32000
80001600022050240003200044100
Kiwango cha sampuli cha sauti inayozalishwa.
audio_setting.bitratesi lazima
Ainaenum
Chaguomsingi128000
3200064000128000256000
Kiwango cha biti cha sauti inayozalishwa.
audio_setting.formatsi lazima
Ainaenum
Chaguomsingimp3
mp3pcmflac
Umbizo la sauti.
audio_setting.channelsi lazima
Ainaenum
Chaguomsingi1
12
Idadi ya njia za sauti: 1 kwa mono au 2 kwa stereo.
language_boostsi lazima
Ainaenum
ChineseChinese,YueEnglishArabicRussianSpanishFrenchPortugueseGermanTurkishDutchUkrainianVietnameseIndonesianJapaneseItalian
+22 zaidiKoreanThaiPolishRomanianGreekCzechFinnishHindiBulgarianDanishHebrewMalaySlovakSwedishCroatianHungarianNorwegianSlovenianCatalanNynorskAfrikaansauto
Huboresha utambuzi kwa lugha na lahaja zilizochaguliwa.
output_formatsi lazima
Ainaenum
Chaguomsingihex
urlhex
Umbizo la maudhui ya tokeo; hutumika tu kwa majibu yasiyotiririshwa.
pronunciation_dictsi lazima
Ainaobject
Kamusi maalum ya matamshi inayotumika kubadilisha maandishi.
pronunciation_dict.tone_listsi lazima
Ainastring[]
Orodha ya vibadilisho vya matamshi inayotumia sintaksia ['text/(pronunciation)', ...], kwa mfano ['燕少飞/(yan4)(shao3)(fei1)']. Nambari za toni za Kichina huanzia 1 hadi 5.
inahitajika

Tokeo

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "minimax/speech-02-hd",
  "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": 5,
    "usd": "0.005",
    "charged": 5,
    "refunded": 0
  },
  "input": {
    "text": "Hello from Doitong. This is a short test sentence."
  },
  "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
    },
    "duration_ms": 1
  },
  "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}Faili ya sauti iliyotengenezwa kupitia uzalishaji.
duration_ms
integerUrefu wa sauti, unaopimwa kwa milisekunde.

Miundo zaidi: Maandishi hadi Matamshi

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/minimax/speech-02-hd.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt