AI article
llama.cpp 0.9.0 Ships Chatterbox TTS and OCP FP8 — Local Speech Still Dies on the Windows Capture Path
Community description: llama.cpp v0.9.0 adds Chatterbox TTS, Nemotron Transcribe, and FP8 E4M3. On Windows the capture stack still owns the latency budget for real-time audio.
Dev.to | Nov 5, 2026 | devs
Automated excerpt
Conversion still follows the usual GGUF path. On Windows the capture path still owns the budget. You get first-class Chatterbox support, Nemotron Transcribe, better multi-sequence efficiency, and FP8 without a new runtime.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.