Skip to main content
Core.Today
|
MiniMaxFastHigh

MiniMax Speech 2.8 Turbo

Low-latency MiniMax Speech 2.8 Turbo with under 250ms latency, 40+ languages, voice cloning, natural interjections, and real-time pricing. Ideal for interactive and real-time applications.

142 credits
per 1000 characters (0.135 credits/char, billed per character)
Under 250ms latency for real-time use
40+ language support
Natural interjections (laughs, sighs, coughs, etc.)
Voice cloning from short audio samples
Emotional expression control
Pause markers and pronunciation control

Run it right now

Test this model instantly in the Console Playground — no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "minimax/speech-2.8-turbo",
  "input": {
    "text": "안녕하세요! (laughs) 코어닷투데이에 오신 것을 환영합니다. <#0.3#> 최고의 AI 음성을 빠르게 경험해 보세요!",
    "voice_id": "Korean_CheerfulLittleSister",
    "emotion": "happy",
    "speed": 1,
    "language_boost": "Korean"
  }
}'

Voice Gallery

Preview 73 preset voices

엉뚱한 소녀F
활발한 소녀F
용감한 여전사F
차분한 숙녀F
따뜻한 여성F
매력적인 언니F
매력적인 여동생F
발랄한 여동생F
소꿉친구 소녀F
차가운 소녀F
카리스마 여왕F
우아한 공주F
매혹적인 언니F
다정한 언니F
부드러운 여성F
도도한 숙녀F
성숙한 여성F
신비로운 소녀F
개성 있는 소녀F
듬직한 언니F
당당한 소녀F
수줍은 소녀F
편안한 여성F
달콤한 소녀F
사려 깊은 여성F
현명한 엘프F
운동하는 학생M
용감한 모험가M
용감한 청년M
차분한 신사M
쾌활한 남자친구M
쾌활한 후배M
건방진 남자M
차가운 청년M
자신감 있는 보스M
배려하는 선배M
강인한 남성M
열정적인 십대M
온화한 보스M
순수한 소년M
지적인 남성M
지적인 선배M
고독한 전사M
긍정적인 청년M
매력적인 남자M
소유욕 강한 남자M
듬직한 청년M
엄격한 보스M
지혜로운 선생님M
Wise Lady (Default)F
Expressive NarratorM
Calm WomanF
Deep Voice ManM
Friendly Person-
Captivating StorytellerM
Kind LadyF
Gentle ButlerM
다정한 사람-
영감을 주는 소녀F
깊은 목소리 남성M
차분한 여성F
캐주얼한 남자M
활발한 소녀F
인내심 있는 남성M
젊은 기사M
결단력 있는 남성M
사랑스러운 소녀F
예의 바른 소년M
위엄 있는 태도M
우아한 남성M
수녀원장F
달콤한 소녀 2F
활기찬 소녀F

Sample: "Hello? Welcome to Core.Today" · Click voice_id to copy

Parameters

ParameterTypeRequiredDefaultDescription
textstringYes-Text to narrate (max 10,000 characters). Use <#0.5#> to insert pauses. Supports interjections: (laughs), (sighs), (coughs), (gasps), (humming), (whistles), (sneezes), etc.
voice_idstringNoEnglish_WiseladyVoice preset or cloned voice ID. 17+ built-in voices available.
speednumberNo1Speech speed multiplier (0.5-2.0)
volumenumberNo1Relative loudness. 1.0 is default MiniMax gain. Range 0–10.
pitchintegerNo0Semitone offset (-12 to +12)
emotionstringNoautoDelivery style
autohappysadangryfearfuldisgustedsurprisedcalmfluentneutral
english_normalizationbooleanNofalseImprove number/date reading for English text (adds a small amount of latency).
sample_rateintegerNo32000Audio sample rate in Hz.
80001600022050240003200044100
bitrateintegerNo128000MP3 bitrate in bits per second. Only used when audio_format is mp3.
3200064000128000256000
audio_formatstringNomp3File format for the generated audio. Choose mp3 for general use, wav/flac for lossless, or pcm for raw bytes.
mp3wavflacpcm
channelstringNomonomono for 1 channel (default), stereo for 2 channels.
monostereo
subtitle_enablebooleanNofalseReserved: the upstream currently returns audio only — no subtitle data is included even when enabled
language_booststringNoNoneLanguage hint for better pronunciation
NoneAutomaticChineseChinese,YueCantoneseEnglishArabicRussianSpanishFrenchPortugueseGermanTurkishDutchUkrainianVietnameseIndonesianJapaneseItalianKoreanThaiPolishRomanianGreekCzechFinnishHindiBulgarianDanishHebrewMalayPersianSlovakSwedishCroatianFilipinoHungarianNorwegianSlovenianCatalanNynorskTamilAfrikaans

Common Parameters

Common parameters used when calling POST /v1/predictions.

ParameterTypeRequiredDefaultDescription
modelstringYes-Model identifier
inputobjectYes-Object containing the model-specific parameters from the table above
output_folderstringNo-Folder path for output files (max 256 chars, '..' not allowed)
webhook_urlstringNo-Webhook URL to call on completion
is_publicbooleanNofalseIf true, output files are also available via permanent public URLs

Examples

Interactive Voice Agent

Generate low-latency voice response with natural interjections

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "minimax/speech-2.8-turbo",
  "input": {
    "text": "안녕하세요! (laughs) 코어닷투데이에 오신 것을 환영합니다. <#0.3#> 최고의 AI 음성을 빠르게 경험해 보세요!",
    "voice_id": "Korean_CheerfulLittleSister",
    "emotion": "happy",
    "speed": 1,
    "language_boost": "Korean"
  }
}'

Tips & Best Practices

1Best choice for real-time applications where latency under 250ms matters
2Use interjection tags like (laughs), (sighs) for more natural delivery
3Insert pauses with <#x#> markers for better pacing (0.01-99.99 seconds)
4Set speed to 1.1-1.2 for chatbot responses to feel more responsive
5Use language_boost for non-English text to improve pronunciation accuracy
6For production-quality output, consider Speech 2.8 HD instead
7subtitle_enable is accepted but the upstream does not return subtitle data yet — responses contain audio only

Use Cases

Real-time voice assistants and agents
Live streaming and interactive content
Customer service chatbots
Game character voices
Multilingual content localization