ElevenLabs wants to run your voice agent. Here’s what developers give up.

ElevenLabs introduced Eleven Realtime, offering two managed voice-agent models that integrate speech recognition, reasoning, and voice generation in a cascaded architecture. The managed approach reduces development overhead for turn-taking and interruption handling but prevents developers from independently selecting or configuring the underlying models. A Custom mode alternative allows full flexibility but requires developers to build and maintain their own stack.

Summary and key points written by AI from the headline and a short excerpt, so they can be incomplete or wrong. The New Stack did the reporting; read the original for the full story.