Lewis Dwyer is a software engineer and technical writer at Ritza. He contributes hands-on testing and writing on developer tools and AI products to TechStackups.
15 articles
A hands-on comparison of Cartesia Sonic and ElevenLabs across quality, latency, price, and control, with the audio clips so you can judge for yourself.
We built Otto, a meeting assistant that listens to any call and answers out loud when addressed by name. Here's how we used Deepgram's Nova-3 transcription and Aura voices to make it work in real time.
We tested the leading realtime voice agent APIs head to head.
We ran 16 AI voice providers through the same scene from Pride & Prejudice. Now it's your turn to pick the winner, blind.
A practical blind comparison of xAI's Grok TTS and OpenAI's gpt-realtime-2 voice model across six real-world scenarios.
xAI's Grok TTS offers expressive speech tags, a realtime voice agent API, and pricing that undercuts ElevenLabs by 12x. Here's what it actually does.
Add Orbital to two REST APIs and replace manual join code with a single TaxiQL query. Covers Taxi schemas, Docker Compose setup, and the .env step that isn't in the official docs.
We tested Orbital's agent experience across discoverability and integration. Four prompts including a web search failed to surface it. A quickstart guide cut integration cost by 30% and produced a more correct result.
I put ElevenLabs and Smallest.ai head-to-head across TTS voice quality, realtime voice agents, voice cloning, latency, and cost.
I integrated the same app with Infisical twice, once with a quickstart I'd written from experience and once without. The guided run cost half as much, took half as many context lines, and used the integration approach Infisical actually recommends.
We tested Prefect's agent experience across four stages (discoverability, onboarding, integration, and agent tooling). Here's every score and what it took to get there.
Can an AI agent log into WordPress, write a post, and publish it, without ever seeing your password?
I used Entire's Checkpoints CLI to track a Claude Code agent building a real project. Here's what the session data looks like, how rewind works, and what you should know before adopting it.
AI agent auth assumes OAuth and tokens, but agents still need plain old passwords for databases, APIs, and legacy services. I tested three approaches to credential security for AI coding agents.
A step-by-step guide on how to set up VS Code, GitHub, and AMP Code for technical writing on macOS.
