Dža ko lil

MiniMax Speech-02 HD

Integriruj

Modelosko id 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"

Kava mangipen: $0.005 5 API krediti Phir les kate

Lel API klidin
MiniMax · Audio

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 50 / 5000

Speech inputosko teksto, limitime ko 5000 znaki taj mangindoj najman 1 znako savo na si whitespace.

Lučhe output_format · language_boost · enable_safety_checker · voice_setting · audio_setting · pronunciation_dict
output_format standardno hex

Formato e sadržaja rezultatosko; važil samo vaš nestrimingano mangipena.

Lačharel recognition vaš avrirodime chiba taj dialecta.

standardno {"english_normalizati...

Settings vaš e voiceski konfiguracija.

Settinga vaš konfiguracija e audioski.

Personalizirime dictionary pronuncacijengo, savo zameninel tekstos.

POST /run/minimax/speech-02-hd?wait=20 hesab → $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"

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 MiniMax Speech-02 HD

Kerel vakeriben dži 5000 karakterendar `text` sa HD kvaliteto e Speech-02-esko. Šaj te lačhares o glaso vaš `voice_setting`, te lačhares `audio_setting`, te upotrebinel `pronunciation_dict`, thaj te biris `language_boost` andar 38 opcije. `output_format` šaj te ovel url vaj hex. O rezultato lel o audio fajlo thaj lesko trajo andro milisekunde.

Parametra

NavTip standardnoMuklo Vakeripe
enable_safety_checkeropcionalno
Tipboolean
standardnotrue
Screening šaj te avel relaksirime te postavil pes false, numa kana o manglo si autorizuime.
texttrubul
Tipstring
≤ 5,000 simbolura
Speech inputosko teksto, limitime ko 5000 znaki taj mangindoj najman 1 znako savo na si whitespace.
voice_settingopcionalno
Tipobject
standardno{"english_normalization":false,"pitch":0,"speed":1,"voice_id":"Wise_Woman","vol":1}
Settings vaš e voiceski konfiguracija.
voice_setting.voice_idopcionalno
Tipstring
standardnoWise_Woman
≥ 1 characters
Predefined voice identifier savo lelpe vaš speech synthesis.
voice_setting.speedopcionalno
Tipnumber
standardno1
0.5 – 2
Speaking rate, katar 0.5 dži 2.0.
voice_setting.volopcionalno
Tipnumber
standardno1
0.01 – 10
E rezultatosko glasosko zor, katar 0 dži ko 10.
voice_setting.pitchopcionalno
Tipinteger
standardno0
-12 – 12
Voicesko pitch, katar -12 dži 12.
voice_setting.emotionopcionalno
Tipenum
happysadangryfearfuldisgustedsurprisedneutral
Emotional tone e synthesized speechosko.
voice_setting.english_normalizationopcionalno
Tipboolean
standardnofalse
English text-normalization option savo del tikno additional latency vaš maj lačho čitavipe e number-engo.
audio_settingopcionalno
Tipobject
Settinga vaš konfiguracija e audioski.
audio_setting.sample_rateopcionalno
Tipenum
standardno32000
80001600022050240003200044100
Sampling rate e generirime audiosko.
audio_setting.bitrateopcionalno
Tipenum
standardno128000
3200064000128000256000
Bitrate e generirime audiosko.
audio_setting.formatopcionalno
Tipenum
standardnomp3
mp3pcmflac
Formato e audiosko.
audio_setting.channelopcionalno
Tipenum
standardno1
12
Audio channel count: 1 vaš mono vaj 2 vaš stereo.
language_boostopcionalno
Tipenum
ChineseChinese,YueEnglishArabicRussianSpanishFrenchPortugueseGermanTurkishDutchUkrainianVietnameseIndonesianJapaneseItalian
+22 averKoreanThaiPolishRomanianGreekCzechFinnishHindiBulgarianDanishHebrewMalaySlovakSwedishCroatianHungarianNorwegianSlovenianCatalanNynorskAfrikaansauto
Lačharel recognition vaš avrirodime chiba taj dialecta.
output_formatopcionalno
Tipenum
standardnohex
urlhex
Formato e sadržaja rezultatosko; važil samo vaš nestrimingano mangipena.
pronunciation_dictopcionalno
Tipobject
Personalizirime dictionary pronuncacijengo, savo zameninel tekstos.
pronunciation_dict.tone_listopcionalno
Tipstring[]
Lista zamenipaskiri pronuncacijengo e sintaksasa ['text/(pronunciation)', ...], sar ['燕少飞/(yan4)(shao3)(fei1)']. E kinesikane tonalno ginavena si 1–5.
trubul

Rezultato

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"
  }
}
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
audio
object {url, content_type, file_name, file_size}Audio fajlo kerdo generaciatar.
duration_ms
integerAudio-duracija, merime milisekundenca.

Bute modeli: Teksto ko Lav

AI agentenge: kadija rig sar Markdown si kate https://doitong.com/rom/developers/models/minimax/speech-02-hd.md. Sa e modelura thaj e gidura: https://doitong.com/developers/llms.txt