Skip to main content
Core.Today
|
MiniMaxFastHigh

MiniMax Speech 2.6 Turbo

Fast multilingual text-to-speech with emotional control, optimized for real-time applications with low latency.

108 credits
per 1000 characters (0.108 credits/char, billed per character)
Ultra-low latency synthesis
Real-time streaming support
300+ voice presets
Emotional expression
Multilingual TTS

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-2.6-turbo",
  "input": {
    "text": "์•ˆ๋…•ํ•˜์„ธ์š”, ์ฝ”์–ด๋‹ทํˆฌ๋ฐ์ด์ž…๋‹ˆ๋‹ค. ๊ทผ์ฒ˜์— ๋ง›์ง‘ 3๊ณณ์„ ์ฐพ์•˜์–ด์š”. ์˜ˆ์•ฝํ•ด ๋“œ๋ฆด๊นŒ์š”?",
    "voice_id": "Korean_FriendlyBigSister",
    "emotion": "happy",
    "speed": 1.1,
    "language_boost": "Korean"
  }
}'

Parameters

ParameterTypeRequiredDefaultDescription
textstringYes-Text to narrate (max 10,000 characters)
voice_idstringNoWise_WomanVoice preset or cloned voice ID
emotionstringNoautoDelivery style
autohappysadangryfearfuldisgustedsurprisedcalmneutral
speednumberNo1Speech speed multiplier (0.5-2.0)
language_booststringNoNoneLanguage hint for better pronunciation
pitchintegerNo0Semitone offset (-12 to +12)

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

Chatbot Response

Generate fast chatbot voice response

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-2.6-turbo",
  "input": {
    "text": "์•ˆ๋…•ํ•˜์„ธ์š”, ์ฝ”์–ด๋‹ทํˆฌ๋ฐ์ด์ž…๋‹ˆ๋‹ค. ๊ทผ์ฒ˜์— ๋ง›์ง‘ 3๊ณณ์„ ์ฐพ์•˜์–ด์š”. ์˜ˆ์•ฝํ•ด ๋“œ๋ฆด๊นŒ์š”?",
    "voice_id": "Korean_FriendlyBigSister",
    "emotion": "happy",
    "speed": 1.1,
    "language_boost": "Korean"
  }
}'

Tips & Best Practices

1Ideal for real-time applications where latency under 500ms is critical
2Use language_boost when mixing multiple languages in a single request
3Set speed to 1.1-1.2 for chatbot responses to feel more responsive
4Combine with streaming APIs for the lowest perceived latency

Use Cases

Real-time applications
Voice chatbots
Live translation
Interactive media
Streaming platforms