Spaces:

gnumanth
/

phonellm-xkcd-voice-agent

Paused

App Files Files Community

phonellm-xkcd-voice-agent / README.md

gnumanth

feat: load pipecat-ai/phonellm-alpha-1 directly in Space with full tool calling and comic UI

2d10adb 7 days ago

preview code

Raw

History Blame Contribute Delete

1.1 kB

A newer version of the Gradio SDK is available: 6.26.0

Upgrade

metadata

title: PhoneLLM Pipecat XKCD Voice Agent
emoji: 🎙️
colorFrom: indigo
colorTo: blue
sdk: gradio
sdk_version: 5.20.0
app_file: app.py
pinned: false
license: mit
short_description: PhoneLLM Pipecat voice agent with live XKCD tools
models:
  - pipecat-ai/phonellm-alpha-1

🎙️ PhoneLLM + Pipecat XKCD Voice Agent

This Space loads and serves pipecat-ai/phonellm-alpha-1 (NVIDIA Nemotron 3 Nano 30B architecture) integrated with a live Pipecat Voice Agent pipeline.

The model autonomously reasons over voice turns with temperature=0 (and thinking disabled), making live tool calls to the CORS-enabled XKCD API at https://xkcd.hemanth.deno.net/ to fetch comics and speak back the punchline.

🛠️ Architecture

LLM Engine: Direct in-process loading of pipecat-ai/phonellm-alpha-1 with 4-bit / 8-bit quantization & bfloat16.
Tool Execution: Real-time API integration with https://xkcd.hemanth.deno.net/.
Voice UI: Interactive comic-styled voice interface with live XKCD strip visualizer.