Daily introduces PhoneLLM, an open model for voice agents

Loading video

Daily co-founder introduces PhoneLLM, an open model for voice agents matching GPT-5.6 Terra on typical voice tasks at 1/3 the latency and 1/18 the cost, built for low-latency tool calling and instruction following.

语音智能体 PhoneLLM 开源模型低延迟工具调用指令跟随 voice agent open-source LLM Daily pipecat 语音交互 Twitter

Category: research

Author: @kwindla

Date: 2026-08-27T00:00:00

Duration: 208.2s

Source: https://x.com/kwindla/status/2093014818647339026

Thea: Towards the Harness of Embodied Agents

Thea: Towards the Harness of Embodied Agents

@walterzhu8 · 12 views · 2026-08-13

具身智能Embodied AIAgent

ARDY robot with voice control in Godot via speech-to-speech

ARDY robot with voice control in Godot via speech-to-speech

@neuralisa · 2 views · 2026-07-22

ARDY语音交互speech-to-speech

Inflatable Baymax Costume as Whole-Body Robotic Skin

Inflatable Baymax Costume as Whole-Body Robotic Skin

@lukas_m_ziegler · 31 views · 2026-08-31

充气皮肤全身触觉人形机器人

Forests for ThreeJS: Procedural Forest Generation in Super Terrain Editor

Forests for ThreeJS: Procedural Forest Generation in Super Terrain Editor

@alightinastorm · 26 views · 2026-08-31

ThreeJS森林生成程序化生成

RoboChemist: Fully Autonomous Wet-Lab Chemistry Robot

RoboChemist: Fully Autonomous Wet-Lab Chemistry Robot

@LeoKharon · 50 views · 2026-08-30

RoboChemist实验室自动化清华AIR

Zetta ζ: Closed-Loop Recovery Harness on Frozen VLA Policies

Zetta ζ: Closed-Loop Recovery Harness on Frozen VLA Policies

@techniahqrobot · 52 views · 2026-08-30

ZettaVLA失败恢复