ElevenLabs has launched two new speech-to-speech models named Eleven Realtime. The Max variant scores 98.8 percent on the Big Bench Audio benchmark with a 0.57-second response time. ElevenLabs states no model on the Artificial Analysis leaderboard is currently both faster and more accurate. The smaller v1 Mini is built for natural conversations at lower cost and can detect when someone finishes speaking or merely says mm-hmm. V1 Max targets more complex tasks like customer support. Both models are available through the ElevenAgents platform and an OpenAI-compatible Realtime API. Pricing is per minute plus token costs, with v1 Max costing more than v1 Mini. Full details are on the ElevenLabs pricing page.
These tools aim to reduce latency in voice interactions while maintaining high fidelity. Lower response times help conversations feel more natural during live calls. Distinct pricing tiers allow developers to choose between speed and cost depending on their specific use case.
* Models accessible via ElevenAgents and OpenAI-compatible API
* v1 Max includes advanced pause detection for complex dialogues
* Pricing structure combines per-minute fees with token costs
