Elevenlabs releases two Eleven Realtime models for voice conversations
Elevenlabs has made Eleven Realtime v1 Mini and Eleven Realtime v1 Max available through ElevenAgents and the Realtime API. According to the company, the Max variant has a response time of 0.57 seconds. Billing combines a per-minute rate with token costs.
Elevenlabs has released Eleven Realtime v1 Mini and Eleven Realtime v1 Max for real-time voice conversations. Both models are available through the ElevenAgents platform and through a Realtime API compatible with the interface provided by OpenAI.
According to Elevenlabs, Eleven Realtime v1 Mini is designed for natural conversations at lower costs and can distinguish between someone finishing speaking and simply acknowledging what is being said. Eleven Realtime v1 Max targets more complex tasks, such as customer support. According to the company, it achieves a score of 98.8 % on Big Bench Audio and a response time of 0.57 seconds.
Billing combines a per-minute rate with token costs. Eleven Realtime v1 Max is more expensive than Eleven Realtime v1 Mini; the source links to detailed pricing from Elevenlabs.
Why it matters
Voice application developers have two variants available for conversations of varying complexity. When choosing, they can assess end-of-speech detection, response time and price; however, the reported performance results are claims made by Elevenlabs.
Two audiences, two different impacts
What this means
For individuals
Developers can integrate the new models into a voice application through a Realtime API compatible with the interface provided by OpenAI.
For a business
For a company considering voice-based customer support, costs include both a per-minute rate and token usage. Call duration alone is therefore insufficient to estimate operating costs.
ProcessesCheck the original
Event sources
only one source so far · 1 publisher, 1 independent. We count feeds from the same owner only once.