K2-k2/QuickTalk-AI

1---2title: QuickTalk AI3emoji: 👀4colorFrom: red5colorTo: yellow6sdk: streamlit7sdk_version: 1.35.08app_file: app.py9pinned: false10license: apache-2.011---12 13# 🎙️ QuickTalk AI14 15QuickTalk AI is a high-performance audio intelligence tool that transforms long-form content—like podcasts and videos—into concise, 30-second audio briefs. Built with **Streamlit**, **OpenAI Whisper**, and **Google Gemini 2.5 Flash**, it automates the "listen, summarize, and speak" workflow.16 17 18 19## 🌟 Key Features20* **Multimodal Input:** Support for both video (MP4) and audio (MP3) uploads.21* **Whisper STT:** Uses OpenAI's Whisper model to accurately transcribe spoken content.22* **Gemini 2.5 Summarization:** Leverages Google's latest Flash model to distill transcripts into three punchy, high-impact bullet points.23* **Voice Briefing:** Automatically converts the AI summary back into a high-quality audio file using gTTS.24* **Transcript Access:** Toggleable view for the full extracted text.25 26## 🚀 Deployment on Hugging Face Spaces27 28To deploy this successfully, follow these steps:29 301.  **SDK:** Select **Streamlit**.312.  **Secret Keys:** Add your Gemini API Key in **Settings > Variables and Secrets** as `GOOGLE_API_KEY_N`.323.  **Requirements:** Your `requirements.txt` must include:33    ```text34    streamlit35    openai-whisper36    torch37    google-generativeai38    moviepy39    gTTS40    yt-dlp41    ```424.  **System Packages:** Create a `packages.txt` file in your repository and add:43    ```text44    ffmpeg45    ```46 47## 🏗️ The Tech Stack48* **Frontend:** Streamlit (UI/UX)49* **Audio Extraction:** MoviePy (Video-to-Audio conversion)50* **Speech-to-Text:** OpenAI Whisper (Base Model)51* **Intelligence:** Google Gemini 2.5 Flash52* **Speech Synthesis:** gTTS (Google Text-to-Speech)53 54## 💻 Local Setup55```bash56# 1. Clone the repository57git clone [https://huggingface.co/spaces/K2-k2/QuickTalk-AI58](https://huggingface.co/spaces/K2-k2/QuickTalk-AI59)60 61# 2. Install dependencies62pip install -r requirements.txt63 64# 3. Set your Environment Variable65# (On Windows use 'set', on Mac/Linux use 'export')66export GOOGLE_API_KEY_N="your_api_key_here"67 68# 4. Run the app69streamlit run app.py70```71 72Developed by **Kesar Agarwal** an aspiring AI Engineer focused on creating accessible, agentic AI tools.73 74Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference