Date: 12/27/2025

Watch the Video

Weekly AI/No-Code Favorites: Local TTS Revolution with Chatterbox

For a long time, text-to-speech has basically meant paid APIs and cloud billing.

In this video, I’m taking a real look at Chatterbox. An MIT-licensed, open-source TTS model from Resemble AI that you can run completely locally. No API keys, no usage limits, and no vendor lock-in.

🔗 Relevant Links
Chatterbox TTS Repo: https://github.com/resemble-ai/chatterbox

❤️ More about us
Radically better observability stack: https://betterstack.com/
Written tutorials: https://betterstack.com/community/
Example projects: https://github.com/BetterStackHQ

📱 Socials
Twitter: https://twitter.com/betterstackhq
Instagram: https://www.instagram.com/betterstackhq/
TikTok: https://www.tiktok.com/@betterstack
LinkedIn: https://www.linkedin.com/company/betterstack

📌 Chapters:
0:00 – Local Text-to-Speech (Why This Matters Now)
0:25 – Model Breakdown: Turbo vs Multilingual
1:09 – Real-Time Turbo Demo with Expressions
2:10 – Why Developers Should Care (Cost, Control, Infra)
2:44 – Limitations & Known Issues (Be Honest)
3:51 – Ecosystem, Momentum & Real-World Adoption
4:17 – Final Take & Who Should Use This

Sharing videos I’ve liked this week on no-code/low-code AI tools—perfect for devs ditching cloud dependencies!

Date: 12/27/2025

Watch the Video

AI Automation Alert: Google’s Gemini 3.0 Changes Everything for No-Code Workflows

Loved this deep dive into Gemini 3.0’s “Computer Use” feature—Google’s free AI agent that browses, clicks, types, and automates real apps like a human, no scripts or APIs needed. Perfect for no-code/low-code builders tackling UI tasks, RPA, or agentic AI. It’s fast, accurate, and ranked #1—game-changer for ops, QA, and everyday automation.

Watch now: Google’s Gemini 3.0 Computer Use Video
Try it: Gemini Browser

NoCode #LowCode #AIAutomation #Gemini3 #AgenticAI

Date: 12/26/2025

Watch the Video

Weekly AI & Low-Code Picks: Apple Silicon Magic for Devs

Loving these videos on no-code/low-code AI workflows using Apple hardware—perfect for running local LLMs, clustering minis, and boosting productivity without heavy setups. Highlights from my likes this week:

• Mac Mini Clusters Unleashed: Alex Ziskind breaks down building M3 Ultra clusters for distributed ML with MLX—Apple fixed the bottleneck, now it’s smooth sailing for 70B models. Watch here + EXO repo: github.com/exo-explore/exo

• Cheap Mini Runs 70B LLM: Affordable Apple Silicon crushes big models locally—no cloud needed. Dive in

• FREE Local LLMs on Apple Silicon: Fast setup guide for no-code AI experiments. Tutorial

• INSANE ML on Neural Engine: Low-code tricks to leverage Apple’s hardware for real-time inference. See it

• Dev Setup on Mac: Streamline your low-code environment with Conda and more. Playlist | AI Coding Playlist

Bonus: Start cybersecurity basics with TryHackMe (25% off code: ZISKIND25) for secure AI builds: tryhackme.com/ziskind.

Gear up your no-code AI game—subscribe to Alex: youtube.com/@AZisk. #AICoding #AppleSilicon #LowCode

Date: 12/24/2025

Watch the Video

Fine-Tuning LLMs on AMD Strix Halo: Local Powerhouse Tutorial

Loved this deep dive into fine-tuning large language models (LLMs) right on your desk with the Framework Desktop powered by AMD Ryzen AI Max “Strix Halo.” The creator shares a ready-to-go Jupyter toolbox for seamless setup, letting you tweak Gemma-3, Qwen, and GPT-OSS 20B models using full-parameter training, LoRA, or QLoRA (with 8/4-bit quantization).

Covers everything from dataset prep and unified memory tricks to checkpointing and exporting for inference. Perfect for AI tinkerers in no-code/low-code spaces looking to harness edge hardware without cloud hassle.

Timestamps for quick jumps: Intro (00:00), Toolbox Install (04:09), Gemma-3 Deep Dive (10:49+), LoRA/QLoRA (30:00+), and GPT-OSS (43:08).

Grab the toolbox and notebooks here: GitHub Repo
More resources: Framework Desktop, Gemma Models, Full Playlist

Watch now and level up your local AI game! 🚀

Date: 12/23/2025

Watch the Video

Weekly AI Favorites: Olares – The On-Premise AI Powerhouse?

Hey AI enthusiasts! In my latest roundup of no-code/low-code AI gems, I’m spotlighting this intriguing Kickstarter project: Olares One. Is it the self-hosted AI automation beast we’ve been craving for home labs and office setups? This video dives deep into a hands-on first look, testing it on an Nvidia 3060 Ti to see if it can power 2026 workflows without cloud lock-in.

Key highlights from the review:

• Wipe & Install: Unique boot process (heads up: it erases your drive!) and easy setup for core tools like Ollama (local LLMs) and n8n (workflow automation).
• Integrations Tested: Seamless n8n + Ollama hookup, plus RAGFlow for document handling, vector storage, and even meeting notes.
• The Catch? Concerns over “LarePass” and Cloudflare tunneling – is it truly on-premise, or still cloud-dependent?

Watch the full breakdown here: 🔥 Olares First Look Video
Back the project: Kickstarter Page
Docs & Resources: Olares Docs

Timestamps:
00:00 Intro & Overview
00:37 Initial Impressions
01:49 Setup/Install
03:08 Ollama + n8n Integration
09:41 RAGFlow Deep Dive
10:54 Ad Break & Future Plans

Olares #SelfHostedAI #LocalLLM #n8n #Ollama #HomeLab #AIAutomation #RAGFlow #OpenSource #OnPremise #Nvidia3060Ti #NoCodeAI #LowCode

Support the channel for more AI news: Join Daily AI 👈 What do you think – game-changer or hype? Drop your thoughts below!