README.md

metadata

title: Voice Summarizer
emoji: 🎙️
colorFrom: green
colorTo: blue
sdk: gradio
sdk_version: 6.0.2
app_file: app.py
pinned: false
license: mit

🎙️ Voice Summarizer

Record audio → Get transcript → Get AI summary!

Features

• Whisper transcription (large-v3-turbo)
• Multiple summary styles
• Chained AI pipeline
• No model downloads - uses API

Setup

Add your HF_TOKEN as a Secret in Space Settings.

Environment Variables

• WHISPER_MODEL: Transcription model (default: openai/whisper-large-v3-turbo)
• LLM_MODEL: Summary model (default: Qwen/Qwen2.5-72B-Instruct)