Elevenlabs releases two speech-to-speech models for real-time AI conversations
Elevenlabs releases two new speech-to-speech models designed for real-time AI conversations
- Who
- ElevenLabs
- What
- released two Eleven Realtime speech-to-speech models, v1 Max and v1 Mini
- When
- Quote
Oct 20, 2026 Elevenlabs released two new speech-to-speech models called Eleven Realtime.
What happened
Elevenlabs released Eleven Realtime v1 Max and v1 Mini for real-time AI conversations. Max scores 98.8 percent on Big Bench Audio with a 0.57-second response time and targets complex tasks such as customer support; Mini targets lower-cost natural conversations and distinguishes finished turns from acknowledgments such as "mm-hmm." Both are available through ElevenAgents and an OpenAI-compatible Realtime API, with per-minute pricing plus token costs.
The story so far
ElevenLabs released Eleven Realtime v1 Max and v1 Mini, two speech-to-speech models for real-time AI conversations, now available through ElevenAgents and an OpenAI-compatible Realtime API. Both carry per-minute charges plus token costs, with Max priced higher than Mini. The Decoder reported that Max scores 98.8 percent on Big Bench Audio and has a 0.57-second response time. Max targets complex tasks such as customer support, while Mini targets lower-cost natural conversations and distinguishes completed speaking turns from acknowledgments such as “mm-hmm.”
Keep reading
Latest daily · Issue 27TorchNeuron brings native PyTorch support for Hugging Face models on AWS TrainiumTrending now
Tomorrow at 08:00, a briefing like this arrives in your inbox.
The same kind of briefing as the one above: a few stories worth reading. Free. Mail starts after you confirm, and every letter has a one-click unsubscribe. Read a past issue · 2026-10-20