Ask Your Audio: An AI That Listens, Thinks, and Talks Back
Last Updated on August 29, 2025 by Editorial Team
Author(s): Ran Tao
Originally published on Towards AI.
Audio chatbot with voice RAG using Whisper, DeepSeek, and XTTS
I got tired of scrubbing back and forth in podcasts. Rewinding five times to find a missing point. So I made an application that just tells me the answer — no rewind needed — and even talks back like the speaker. 🎧
This article discusses the creation of an AI application that transcribes audio from podcasts and answers questions in the voice of the original speaker. It outlines the technology stack, including Whisper for speech-to-text, a local LLM for answering questions, and XTTS for text-to-speech, while also providing insights into the coding process and a demonstration via a Streamlit app, emphasizing the potential for further development in real-time chatbot applications using open-source components.
Read the full blog for free on Medium.
Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.
Published via Towards AI
Towards AI Academy
We Build Enterprise-Grade AI. We'll Teach You to Master It Too.
15 engineers. 100,000+ students. Towards AI Academy teaches what actually survives production.
Start free — no commitment:
→ 6-Day Agentic AI Engineering Email Guide — one practical lesson per day
→ Agents Architecture Cheatsheet — 3 years of architecture decisions in 6 pages
Our courses:
→ AI Engineering Certification — 90+ lessons from project selection to deployed product. The most comprehensive practical LLM course out there.
→ Agent Engineering Course — Hands on with production agent architectures, memory, routing, and eval frameworks — built from real enterprise engagements.
→ AI for Work — Understand, evaluate, and apply AI for complex work tasks.
Note: Article content contains the views of the contributing authors and not Towards AI.
Related posts
Recent Posts
