Text-to-speech picked one voice regardless of what language a reply was in.
A dependency-free language detector (script, marker letters, function words)
now decides the language of the whole message once; with the new
"Match the voice to the language of the text" setting the local provider
switches to a catalog model for that language (Kokoro zh/en and Piper models
for 12 languages, downloaded on first use like the existing model) and macOS
say switches to an installed voice whose locale matches. The local voice
picker lists voices of every installed model, and the settings show which
language models are on disk.
The Ukrainian Piper medium build is a character-level model that sherpa-onnx
turns into noise, so the espeak-based Lada build is used instead.
Claude-Session: https://claude.ai/code/session_017TK5JAYDfT3Fotc23UEg98
Bohdan Triapitsyn
391f938334