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
Ultra-realistic text-to-speech with expressive controls (sarcasm, whisper, giggle)
Voice cloning from audio samples or text prompts
10,000+ voices across 70+ languages
Music v2 generation from text prompts, up to 320kbps output
Sound effects and ambient audio generation from prompt or library
Scribe v2 speech-to-text with 98% accuracy and speaker diarization
Dubbing v2 for voice translation with watermark options
ElevenAgents: omnichannel conversational agents via voice, chat, email, WhatsApp
Low-latency models: Eleven Flash ~75ms, Eleven Turbo v2.5
Guardrails and workflows for agent deployment
Analytics and A/B testing for conversational agents
Image and video generation (Veo, Sora, Wan, Kling, Seedance)
Ads Engine for AI-powered ad production in ElevenCreative
Flows Agent for automated creative workflows
SynthID watermarking for AI-generated audio detection