Ruka hadi kwenye maudhui

MiniMax Speech 2.8 HD

Unganisha

Kitambulisho cha modeli minimax/speech-2.8-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-2.8-hd?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Welcome aboard. Tonight we cruise along the northern coast, where the lighthouse has guided sailors home for two hundred years. Find a warm seat on the upper deck and enjoy the view."
  }'

# 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: $ 0.019 salio za API 19 Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
MiniMax Maandishi hadi Matamshi #voiceover#multilingual#hd

Ubadilishaji wa maandishi kuwa sauti wa MiniMax wa ubora wa juu katika lugha 30+, wenye kusitisha, hisia na udhibiti wa matamshi.

Mifano

Tokeo · ~10 s

MaelekezoWelcome aboard. Tonight we cruise along the northern coast, where the lighthouse has guided sailors home for two hundred years. Find a warm seat on the upper deck and enjoy the view.

$ 0.019 · salio za API 19

Unda ombi

Vidhibiti vinazalishwa kutoka kwenye schema ya modeli. Msimbo na bei husasishwa unapovibadilisha.

•inahitajika 182 / 10000

Maandishi ya usanisi wa usemi, yenye mapumziko yaliyobainishwa na `<#x#>` ambapo x huanzia 0.01 hadi 99.99 sekunde. Alama za viingilizi zinazopatikana ni `(laughs)`, `(sighs)`, `(coughs)`, `(clears throat)`, `(gasps)`, `(sniffs)`, `(groans)`, na `(yawns)`.

Ya kina output_format · language_boost · voice_setting · audio_setting · pronunciation_dict · normalization_setting · voice_modify
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.

Mipangilio inayodhibiti usanifishaji wa sauti.

Mipangilio ya kurekebisha toni, nguvu na timbre ya sauti.

POST /run/minimax/speech-2.8-hd?wait=20 makadirio → $ 0.019
# 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-2.8-hd?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Welcome aboard. Tonight we cruise along the northern coast, where the lighthouse has guided sailors home for two hundred years. Find a warm seat on the upper deck and enjoy the view."
  }'

# 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 2.8 HD

MiniMax Speech 2.8 HD hutamka maandishi katika zaidi ya lugha 30 kwa udhibiti wa kina: alama za kusitisha ndani ya maandishi, kasi ya sauti, toni na ujazo, kamusi maalum za matamshi na athari za sauti. Chagua kati ya sauti zilizojumuishwa na kiwango cha sampuli na umbizo la matokeo.

Vigezo

JinaAina ChaguomsingiInaruhusiwa Maelezo
promptinahitajika
Ainastring
≤ herufi 10,000
Maandishi ya usanisi wa usemi, yenye mapumziko yaliyobainishwa na `<#x#>` ambapo x huanzia 0.01 hadi 99.99 sekunde. Alama za viingilizi zinazopatikana ni `(laughs)`, `(sighs)`, `(coughs)`, `(clears throat)`, `(gasps)`, `(sniffs)`, `(groans)`, na `(yawns)`.
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.
normalization_settingsi lazima
Ainaobject
Mipangilio inayodhibiti usanifishaji wa sauti.
normalization_setting.enabledsi lazima
Ainaboolean
Chaguomsingitrue
Huwasha usanifishaji wa sauti.
normalization_setting.target_loudnesssi lazima
Ainanumber
Chaguomsingi-18
-70 – -10
Sauti inayotakiwa, inayopimwa kwa LUFS; chaguomsingi ni -18.0.
normalization_setting.target_rangesi lazima
Ainanumber
Chaguomsingi8
0 – 20
Masafa ya sauti yanayotakiwa, yanayopimwa kwa LU; chaguomsingi ni 8.0.
normalization_setting.target_peaksi lazima
Ainanumber
Chaguomsingi-0.5
-3 – 0
Kiwango cha kilele kinachotakiwa, kinachopimwa kwa dBTP; chaguomsingi ni -0.5.
voice_modifysi lazima
Ainaobject
Mipangilio ya kurekebisha toni, nguvu na timbre ya sauti.
voice_modify.pitchsi lazima
Ainainteger
Chaguomsingi0
-100 – 100
Udhibiti wa toni unaopimwa kwa semitoni: tumia thamani hasi kushusha sauti au thamani chanya kuiinua. Thamani zinazoruhusiwa ni -100 hadi 100.
voice_modify.intensitysi lazima
Ainainteger
Chaguomsingi0
-100 – 100
Udhibiti wa nguvu ya sauti unaofanya usemi uwe na nguvu zaidi kadiri mpangilio unavyoongezeka. Masafa yake yanayoruhusiwa ni -100 hadi 100.
voice_modify.timbresi lazima
Ainainteger
Chaguomsingi0
-100 – 100
Marekebisho ya timbre ya sauti kutoka -100 hadi 100, yanayodhibiti sifa yake ya toni.
inahitajika

Tokeo

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "minimax/speech-2.8-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": 19,
    "usd": "0.019",
    "charged": 19,
    "refunded": 0
  },
  "input": {
    "prompt": "Hello! Welcome to our new studio. <#0.5#> Let's make something wonderful today."
  },
  "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-2.8-hd.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt