Features
Real-time speech-to-text with Flux and Nova-3 models
Text-to-speech with Aura-2 and Aura-1 voices
Unified Voice Agent API (STT+TTS+LLM orchestration)
Flux Multilingual: conversational STT in 10 languages with built-in turn detection and interruption handling
Batch transcription for pre-recorded audio
Self-hosted deployment option
Audio Intelligence API for emotion, sentiment, topic detection
Custom model training for domain-specific accuracy
Speaker diarization and sentiment analysis
WebSocket and REST API integration
Profanity filtering across models
Automatic language detection (Nova-3 Multilingual)
Keyterm Prompting for domain-specific jargon accuracy
Redaction of PII like social security numbers and credit cards
Smart Formatting for punctuation, casing, dates, currency
Pre-recorded speech-to-text (Universal-3.5 Pro, 18 languages)
Pre-recorded speech-to-text (Universal-2, 99 languages)
Real-time streaming speech-to-text (Universal-3.5 Pro Realtime with Context Carryover)
Voice Agent API with built-in turn detection and interruption handling
Speech Understanding API (speaker ID, sentiment, chapters, summaries)
Guardrails for inline PII redaction and content moderation
LLM Gateway routing across GPT, Claude, and Gemini with fallback
Keyterms Prompting to improve accuracy for specific terms
Agent Management API to store and manage agent configurations
HTTP Tool Calling for Voice Agent API (no proxy server needed)
Production-ready Python and TypeScript SDKs
Self-hosted Voice AI Cloud deployment for enterprise
No concurrency limits, no throttles, no forced commitments
Global redundancy and enterprise-grade uptime
Code-switching support (Universal-3.5 Pro)