From the source
ElevenLabs launched Eleven Realtime, a class of speech-to-speech models that each work as a complete voice agent, removing the need to assemble speech recognition, voice activity detection, turn-taking, an LLM and text to speech.
- Both models support more than 90 languages and can use any of the 17,000+ voices in the ElevenLabs library.
- Eleven Realtime v1 Mini is built for natural conversations at low cost, which ElevenLabs recommends for AI assistants, teachers and interactive characters, while v1 Max targets complex tasks such as customer support, lead qualification and multi-step workflows.
- Artificial Analysis evaluated both models independently on three public benchmarks.
- On Big Bench Audio, v1 Max answered 98.8% of 1,000 spoken reasoning questions correctly and v1 Mini 75.9%; v1 Max starts speaking in 0.57 seconds on average and v1 Mini in 0.62 seconds.
- On Full-Duplex-Bench, v1 Mini scored 95.8% and v1 Max 94.1%, and in the Speech Agent Arena v1 Max scored 998 and v1 Mini 988.
- On tool-use tasks v1 Max completed 87.1% and v1 Mini 60.3%, which is why ElevenLabs recommends Max for heavy tool calling.
