Features
Multilingual text-to-speech in 30 languages
Voice cloning with controllable similarity
Voice design from scratch using text prompts
48kHz high-quality audio output
LoRA training for custom voice adaptation
Diffusion-based speech generation
Emotion and prosody control
Node-based workflow in ComfyUI
Supports multiple speaker references
Tokenizer-free architecture
Model weights in safetensors format
Compatible with ComfyUI visual node editing
Open-source and self-hosted
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
