Video · Tech With Tim ·
Python Voice Agent Tutorial: Clone Your Voice & Talk to AI
In short
The video demonstrates a Python voice agent that records speech, transcribes it, sends it to an LLM, and speaks the response using a cloned voice. It uses AssemblyAI and under 100 lines of code, showing a simple foundation for conversational agents such as receptionists or callers.
Key points
- The architecture has five stages: input, speech-to-text, LLM response, text-to-speech, and audio playback.
- A voice clone requires only a 10- to 20-second recording and produces a reusable voice ID.
- The project uses Python, UV, and four dependencies: AssemblyAI, httpx, python-dotenv, and sounddevice.
- The free setup uses Cohere 3.5 through AssemblyAI's LLM gateway.
- Conversation history is stored in a Python list so the agent can remember prior exchanges.
- The final loop listens until the user says goodbye and keeps responses to short spoken replies.
Written by an AI model from the video’s captions and description.
In this video I clone my own voice and build a Python AI agent that talks back to me in it, in under 100 lines of code. You’ll hear the demo at the start, and the clone sounded close to me on the very first version I tried.



