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.

108 credits
per 1000 characters (0.108 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

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txt

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": "μ•ˆλ…•ν•˜μ„Έμš”! (laughs) μ½”μ–΄λ‹·νˆ¬λ°μ΄μ— μ˜€μ‹  것을 ν™˜μ˜ν•©λ‹ˆλ‹€. <#0.3#> 졜고의 AI μŒμ„±μ„ λΉ λ₯΄κ²Œ κ²½ν—˜ν•΄ λ³΄μ„Έμš”!",
    "voice_id": "Korean_CheerfulLittleSister",
    "emotion": "happy",
    "speed": 1,
    "language_boost": "Korean"
  }
}'

Voice Gallery

Preview 73 preset voices

μ—‰λš±ν•œ μ†Œλ…€F
ν™œλ°œν•œ μ†Œλ…€F
μš©κ°ν•œ 여전사F
μ°¨λΆ„ν•œ μˆ™λ…€F
λ”°λœ»ν•œ μ—¬μ„±F
λ§€λ ₯적인 μ–Έλ‹ˆF
λ§€λ ₯적인 여동생F
λ°œλž„ν•œ 여동생F
μ†ŒκΏ‰μΉœκ΅¬ μ†Œλ…€F
μ°¨κ°€μš΄ μ†Œλ…€F
카리슀마 μ—¬μ™•F
μš°μ•„ν•œ 곡주F
맀혹적인 μ–Έλ‹ˆF
λ‹€μ •ν•œ μ–Έλ‹ˆF
λΆ€λ“œλŸ¬μš΄ μ—¬μ„±F
λ„λ„ν•œ μˆ™λ…€F
μ„±μˆ™ν•œ μ—¬μ„±F
μ‹ λΉ„λ‘œμš΄ μ†Œλ…€F
κ°œμ„± μžˆλŠ” μ†Œλ…€F
λ“¬μ§ν•œ μ–Έλ‹ˆF
λ‹Ήλ‹Ήν•œ μ†Œλ…€F
μˆ˜μ€μ€ μ†Œλ…€F
νŽΈμ•ˆν•œ μ—¬μ„±F
λ‹¬μ½€ν•œ μ†Œλ…€F
사렀 κΉŠμ€ μ—¬μ„±F
ν˜„λͺ…ν•œ μ—˜ν”„F
μš΄λ™ν•˜λŠ” 학생M
μš©κ°ν•œ λͺ¨ν—˜κ°€M
μš©κ°ν•œ μ²­λ…„M
μ°¨λΆ„ν•œ 신사M
μΎŒν™œν•œ λ‚¨μžμΉœκ΅¬M
μΎŒν™œν•œ ν›„λ°°M
건방진 λ‚¨μžM
μ°¨κ°€μš΄ μ²­λ…„M
μžμ‹ κ° μžˆλŠ” 보슀M
λ°°λ €ν•˜λŠ” μ„ λ°°M
κ°•μΈν•œ 남성M
열정적인 μ‹­λŒ€M
μ˜¨ν™”ν•œ 보슀M
μˆœμˆ˜ν•œ μ†Œλ…„M
지적인 남성M
지적인 μ„ λ°°M
κ³ λ…ν•œ 전사M
긍정적인 μ²­λ…„M
λ§€λ ₯적인 λ‚¨μžM
μ†Œμœ μš• κ°•ν•œ λ‚¨μžM
λ“¬μ§ν•œ μ²­λ…„M
μ—„κ²©ν•œ 보슀M
μ§€ν˜œλ‘œμš΄ μ„ μƒλ‹˜M
Wise Woman (Default)F
Expressive NarratorM
Calm WomanF
Deep Voice ManM
Friendly Person-
Captivating StorytellerM
Kind LadyF
Gentle ButlerM
λ‹€μ •ν•œ μ‚¬λžŒ-
μ˜κ°μ„ μ£ΌλŠ” μ†Œλ…€F
κΉŠμ€ λͺ©μ†Œλ¦¬ 남성M
μ°¨λΆ„ν•œ μ—¬μ„±F
μΊμ£Όμ–Όν•œ λ‚¨μžM
ν™œλ°œν•œ μ†Œλ…€F
인내심 μžˆλŠ” 남성M
μ Šμ€ 기사M
결단λ ₯ μžˆλŠ” 남성M
μ‚¬λž‘μŠ€λŸ¬μš΄ μ†Œλ…€F
예의 λ°”λ₯Έ μ†Œλ…„M
μœ„μ—„ μžˆλŠ” νƒœλ„M
μš°μ•„ν•œ 남성M
μˆ˜λ…€μ›μž₯F
λ‹¬μ½€ν•œ μ†Œλ…€ 2F
ν™œκΈ°μ°¬ μ†Œλ…€F

Sample: "Hello? Welcome to Core.Today" Β· 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_idstringNoWise_WomanVoice preset or cloned voice ID. 17+ built-in voices available.
emotionstringNoautoDelivery style
autohappysadangryfearfuldisgustedsurprisedcalmfluentneutral
speednumberNo1Speech speed multiplier (0.5-2.0)
pitchintegerNo0Semitone offset (-12 to +12)
language_booststringNoNoneLanguage hint for better pronunciation

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": "μ•ˆλ…•ν•˜μ„Έμš”! (laughs) μ½”μ–΄λ‹·νˆ¬λ°μ΄μ— μ˜€μ‹  것을 ν™˜μ˜ν•©λ‹ˆλ‹€. <#0.3#> 졜고의 AI μŒμ„±μ„ λΉ λ₯΄κ²Œ κ²½ν—˜ν•΄ λ³΄μ„Έμš”!",
    "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

Use Cases

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