Features
Text-to-speech in multiple languages
Diverse natural-sounding voices
HD high-quality synthesis
Turbo low-latency real-time synthesis
Emotional and prosodic variation
Scalable for production workloads
Powered by MiniMax Speech model
Multiple audio format support
Prepaid subscription packs
Free tier for initial testing
Per-call billing for variable usage
Token Plan with monthly quota
Token Plan for Teams with shared credits
Real-time speech-to-text under 1 second latency
Multilingual code-switching (Melia model) for batch transcription
Speaker-aware transcription (diarization)
On-device deployment for Adobe Premiere (offline)
Medical model – up to 50% fewer errors on key medical terms
Health signal detection (fatigue, stress, type 2 diabetes) from 15-second voice clips
Low-latency text-to-speech (English, more languages coming soon)
Batch transcription with microbatching workflow
Custom vocabulary and custom models (Enterprise)
On-premise and private cloud deployment
Zero data logging by default
ISO 27001, HIPAA, SOC 2 Type II compliance
Voice agent API with WebSocket and REST integrations
Alphanumeric recognition for SKUs and IDs
