ElevenLabs releases two real-time speech-to-speech models, v1 Max and v1 Mini
What happened
ElevenLabs released two speech-to-speech models for real-time AI conversation, Eleven Realtime v1 Max and v1 Mini, The Decoder reported on October 21, 2026. v1 Max targets complex tasks such as customer service, scoring 98.8% on the Big Bench Audio benchmark with a 0.57-second response time. v1 Mini targets low-cost natural conversation and can tell when a user has finished speaking versus only making sounds like "mm-hmm."
Written by AI from the coverage · updated 2 hours ago
Coverage
Follow the reports to see the story from different sides.
- The DecoderElevenlabs releases two new speech-to-speech models designed for real-time AI conversations
Elevenlabs 发布 Eleven Realtime v1 Max 和 v1 Mini 两款语音到语音模型，面向实时 AI 对话。v1 Max 在 Big Bench Audio 基准上得分为 98.8%，响应时间为 0.57 秒，面向客服等复杂任务；v1 Mini 主打低成本自然对话，能区分用户说完话与仅发出“嗯哼”等回应。
Heat over time
Heat now 9·Comparable peak 10（Oct 21 04:00）·Comparable change over 24 hours –
The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.