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
Multilingual speech transcription (99+ languages)
To-English speech translation
Zero-shot robustness to accents, noise, technical language
Open-source models and inference code
Encoder-decoder Transformer architecture
Trained on 680,000 hours of diverse data
Log-Mel spectrogram input
30-second audio chunk processing
Multiple model sizes (tiny to large)
Whisper.cpp for CPU inference
Fine-tuning via Hugging Face integration
Turbo model on OpenAI API
OpenAI API at $0.006 per minute