#whisper

Building Li Translate: An Open-Source AI Subtitle Generator That Actually Understands...

I spent the last few weeks testing the absolute crap out of offline, local-first voice-to-text apps....

Sequel to My LLM could not tell a timelapse from real time — so I taught it physics. I build crv, an...

I've been running Whisper locally (via whisper.cpp) on my MacBook for offline voice-to-text, and at...

Apple shipped SpeechAnalyzer in iOS 26 and macOS 26 with zero published accuracy numbers. The first rigorous benchmark just landed: 2.12% word error rate on clean English, beating every on-device Whis

I benchmarked 5 Ollama models against Whisper v3 Turbo on a CPU-only box, chasing a 300ms voice-to-first-byte budget. Two of the five got there. The other three did not, and one of them is the one every tutorial recommends.

In an era where cloud services dominate AI applications, Whisper Studio stands out by bringing...

Top GPUs for local Whisper transcription in 2026 — real-time speeds, VRAM by model size, and budget picks from $150. Large-v3 ready.

Modern voice applications often fail for a simple reason: the speech pipeline is treated as a single...

A few months ago, I started paying closer attention to something most of us experience every day but...

I'm excited to introduce the first release of GSTranscription, an AI-powered audio-to-text...

Run private speech-to-text on your own Mac or PC with bundled whisper.cpp. Mic to text in the composer, on-device, no cloud transcription.