markosveloso / qa-assistant-eleven-labs-voice-cloning

Voice Q&A Using ChatGPT API, Embeddings, Gradio, and Eleven Labs API For Voice Cloning

Voice Q&A With Eleven Labs API, Whisper API, ChatGPT API, Embeddings, Gradio

Video Demo / Tutorial:

https://www.youtube.com/watch?v=Lsn_OR9Fr3s

Setup

You need an Eleven Labs API Key and an OpenAI API Key to use this.

You also need a Python environment.

Install dependencies with:

pip install -r requirements.txt

On OS X, install ffmpeg with:

brew install ffmpeg

API's Used

• Voice Cloning - ElevenLabs

Notebooks, Videos, and Code Used:

• Video #5 Word Embeddings: https://www.youtube.com/watch?v=xzHhZh7F25I
• Video #5 Notebook: https://colab.research.google.com/drive/1tttDqgnWL9yJtmlOFXJqA-BjQ1Pyfpax?usp=sharing
• Video #6 Financial Q&A: https://www.youtube.com/watch?v=hR8xhJgKcJ0
• Video #6 Notebook: https://colab.research.google.com/drive/1cVQNg2-zGQb7qZXFECG6kyq5yVIHyf5o?usp=sharing
• Video #9 ChatGPT API + Whisper API and Gradio: https://www.youtube.com/watch?v=Si0vFx_dJ5Y
• Video #9 Code: https://github.com/hackingthemarkets/chatgpt-api-whisper-api-voice-assistant
• Video #10 Walkthrough: https://www.youtube.com/watch?v=Lsn_OR9Fr3s
• Video #10 Code: https://github.com/hackingthemarkets/qa-assistant-eleven-labs-voice-cloning

Podcasts and YouTube Videos Transcribed to Build the Knowledge Base

• https://www.youtube.com/@TheCompoundNews

Midjourney Images and Prompts

• a full photo of a young financial advisor wearing a Hawaiian shirt, holding a cocktail glass, meeting with his client at a bar, natural lighting, uplight, natural features, photorealistic, highly detailed, cinematic lighting https://s.mj.run/mTbGLb82o8E --iw 2.0 --v 5

• a full photo of a young female financial advisor wearing a Hawaiian shirt, sitting at a bar, natural lighting, uplight, natural features, photorealistic, highly detailed, cinematic lighting https://cdn.theplaylist.net/wp-content/uploads/2018/03/14222302/Scarlett-Johansson-750x400.jpg --iw 2.0 --v 5