Back to Model
P

PhoneLLM Alpha 2

Model Oct 15, 2026

Pipecat's Mini and Max text models for voice-agent pipelines, with tool calling, Pipecat Flows training and short reasoning in Max.

Visit primary link 3 sources attached
Daily's PhoneLLM Max Alpha 2 example conversation shows short reasoning sentences, a changed party size, a reservation tool call and an end-call tool call.
Daily / Pipecat's published example dialogue illustrating microthinking and tool calls. This is an author-provided example, not a verified real customer call or an AITrending reproduction. Source: Daily / Pipecat
ai-agentsself-hosted

What happened lately

PhoneLLM Alpha 2 timeline

Daily announced PhoneLLM Alpha 2 on October 15, 2026. Mini prioritizes speed and size; Max adds a short sentence of reasoning before each response. Both are text models that supply the language and tool-calling component of a voice agent, rather than generating or understanding audio directly.

Daily says the models were trained on synthetic conversations, including Pipecat Flows sessions. The model cards document vLLM serving recipes and temperature zero. Mini runs with reasoning disabled; Max requires reasoning enabled and the Nemotron reasoning parser. Source-reported speed and accuracy comparisons have not been independently reproduced by AITrending. Mini and Max have different license declarations, and the underlying model terms must also be checked before redistribution.