Blog

March 7, 2026

Re-Forge: How We Built a Prose Refinement Engine

We ran 35 controlled experiments to answer a hard question: can a second AI pass reliably improve fiction? Here’s what failed, what broke catastrophically, and what finally delivered a 35% quality lift.

March 6, 2026

Closing the Gap: Building Audiobook-Quality TTS with an 82M Parameter Model

Can a small open TTS model get close to audiobook-quality narration? We tested Kokoro-82M against Gemini, built tooling to measure the differences, and tracked down the exact pipeline issues hurting quality. From dropped sentences to broken pronunciations, this is a practical look at what actually improves long-form TTS.

February 28, 2026

Narration Forge: adding audiobook playback to ProseForge

I built Narration Forge for a simple reason: I wanted something to listen to on my bike rides. That turned into a real ProseForge feature, a practical TTS bake-off between Orpheus, Qwen3-TTS, and Kokoro, and a clear winner that was fast, light, and actually shippable.

February 26, 2026

Images Bring Stories to Life

Images help stories “stick.” Not as final art, but as visual anchors that lock in tone, setting, and character identity—so you can iterate without losing the thread.

February 25, 2026

Why I Started ProseForge

ProseForge began when I realized I wasn’t just writing stories—I was trying to hold onto them. What started as a creative struggle with continuity, memory, and iteration slowly turned into a toolset for building stories without losing the thread.

February 24, 2026

Orchestration Beats Model Swaps

I thought better models would fix story quality in ProseForge. The real gains came from provider stability, orchestration, and stateful continuation design.