Spaces:

gnumanth
/

phonellm-xkcd-voice-agent

Paused

App Files Files Community

phonellm-xkcd-voice-agent / README.md

gnumanth

feat: PhoneLLM + Pipecat XKCD Voice Agent with live tool calling

58eaa29 8 days ago

1.2 kB

title: PhoneLLM Pipecat XKCD Voice Agent
emoji: 🎙️
colorFrom: indigo
colorTo: blue
sdk: static
pinned: false
license: mit
short_description: PhoneLLM & Pipecat voice agent with XKCD tool calling

🎙️ PhoneLLM + Pipecat XKCD Voice Agent

An interactive, real-time voice agent built with the Pipecat architectural model and pipecat-ai/phonellm-alpha-1 (NVIDIA Nemotron 3 Nano 30B-A3B architecture).

The voice agent executes real-time tool calls to the live, CORS-enabled XKCD API at https://xkcd.hemanth.deno.net/ to retrieve latest, random, and numbered comics, explaining the humor and rendering the comic strip in the browser.

🚀 Key Features

PhoneLLM Alpha 1 Optimization: Tuned with temperature: 0 and zero thinking tokens for low-latency voice turns.
Pipecat Tool Calling: Automatically detects intent to call get_latest_xkcd, get_random_xkcd, or get_xkcd_by_number.
Live XKCD Deno API: Connects directly to https://xkcd.hemanth.deno.net/.
Dual Voice & Visual Feedback: Speaks back the punchline and comic explanation while rendering the full comic strip and alt text.