ElevenLabs Realtime

Eleven Realtime is a new class of Speech to Speech models for building natural voice agents. Each model combines speech recognition, turn-taking, LLM, and text to speech tuned together as one system, so you get a well-performing agent from a single model choice. It’s available in ElevenAgents and the Realtime API.

V1 Mini is the lower cost choice for simpler use cases like AI assistants, tutors, and interactive characters. V1 Max adds reasoning capability for more complex tasks like customer support, lead qualification, and multi-step workflows with tool calls.

Create an agent, or open an existing one, and choose v1 Mini or v1 Max from the model dropdown. Your prompt, tools, knowledge base, channels, and settings work as before. Nothing changes for existing agents unless you update them.

It’s OpenAI-compatible. If you’re already on OpenAI’s Realtime API, change the endpoint and model name in the code you have, or run npx skills add elevenlabs/skills --skill openai-realtime-migration and the skill handles setup. OpenAI’s SDK works as is. The migration guide covers the differences. If you’re starting from scratch, we recommend ElevenAgents.

Not at launch. It connects over WebSocket, so a WebRTC integration needs to move to WebSocket first.

No. The Realtime API and ElevenAgents run separately and use different connection protocols. If you need phone, WhatsApp, or contact center channels, a knowledge base, guardrails, testing, or monitoring, build on ElevenAgents.

In ElevenAgents, Realtime models use standard ElevenAgents per-minute pricing plus the LLM cost per token. The model selector in the app shows an estimated cost per minute. Through the Realtime API, you pay per minute of connected audio plus tokens, with the same token prices on every plan. See the pricing page for current rates.

Artificial Analysis evaluated both models independently on Big Bench Audio for speech reasoning, Full-Duplex-Bench for conversational dynamics, and the Speech Agent Arena for human preference and task success. Time to first audio is the average measured on Big Bench Audio.

Monthly price and included credits per plan: Free $0 (10,000 credits); Starter $6 (30,000 credits); Creator $22 (121,000 credits, $11 for the first month); Pro $99 (600,000 credits); Scale $299 (1,800,000 credits, 3 seats); Business $990 (6,000,000 credits, 10 seats); Enterprise is custom. Credits are shared across every product — see the per-product credit costs below.

Each text character you generate consumes credits, with the exact cost depending on the model used. For V2 Multilingual models, 1 text character equals 1 credit. For V2 Flash/Turbo English and V2.5 Flash/Turbo Multilingual models, discounted pricing applies for API usage, costing between 0.5 and 1 credit per character.