Gemini 3.8 Flash TTS with Voice Cloning

In this video, I go through the latest TTS offering from Google with their Gemini 3.8 Flash TTS. Blog: https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-text-to-speech/ Colab: https://colab.research.google.com/drive/1PN3XEXb5385W_V_2tNjXl468mqYGoNgl?usp=sharing Twitter: https://x.com/Sam_Witteveen 🕵️ Interested in building LLM Agents? Fill out the form below Building LLM Agents Form: https://drp.li/dIMes 👨‍💻Github: https://github.com/samwit/llm-tutorials ⏱️Time Stamps: 00:00 Intro 00:53 Flash TTS vs Flash-Lite TTS 01:22 Voice design 02:44 2,000+ voice library 02:58 Voice cloning and guardrails 04:02 Stage directions and non-verbal tags 04:23 Multi-speaker and long-form audio 04:48 Benchmarks 06:53 Pricing 07:19 AI Studio demo 08:45 Colab: Flash vs Flash-Lite 09:53 Colab: Style control 11:05 Colab: Inline tags 11:37 Colab: Voice design 12:38 Colab: Multi-speaker dialogue 13:50 Colab: Voice cloning