Voice Enhancements & Minimax Improvements
-
Minimax Voice Language Support: Enhance multilingual conversations with
MinimaxVoice.languageBoost. Support for 40+ languages including:ChineseandChinese,Yuefor Mandarin and CantoneseEnglish,Spanish,French,German,Japanese,Korean- Regional variants and specialized languages like
Arabic,Hindi,Thai automode for automatic language detection
-
Text Normalization: Improve number reading and formatting with
MinimaxVoice.textNormalizationEnabled. When enabled, spoken numbers, dates, and formatted text are properly pronounced for natural-sounding conversations. -
Enhanced Voice Caching: Voice responses are now cached by default with
MinimaxVoice.cachingEnabledset totrue, reducing latency for repeated phrases and improving overall conversation performance. -
Fallback Voice Configuration: Ensure conversation continuity with
FallbackMinimaxVoicefeaturing the same language boost and text normalization capabilities as the primary voice configuration. -
Speaker Labeling: Track multiple speakers in conversations with
BotMessage.speakerLabel, providing stable speaker identification (e.g., “Speaker 1”) for better conversation analysis and diarization. -
Voice Region Support: Choose optimal performance regions with Minimax’s
worldwide(default) orchinaregional settings for better latency and compliance with local regulations.
Language boost settings help the text-to-speech model better understand context and pronunciation for specific languages, resulting in more natural and accurate voice synthesis.
Voice Quality Features
Support for 40+ languages with automatic detection and language-specific optimizations for natural pronunciation.
Intelligent normalization of numbers, dates, and formatted text for natural-sounding speech synthesis.
Voice caching reduces latency for common phrases, while regional settings optimize for local performance.
Speaker labeling and diarization support for multi-participant conversation analysis and management.