BuzzbeeSCD/openchamber
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(voice): match local and macOS voices to the language of the text

Browse Source 
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
This commit is contained in:
Bohdan Triapitsyn
2026-08-30 02:24:22 +03:00
parent 49f0a9e62f
commit 391f938334
29 changed files with 949 additions and 115 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/ui/src/lib/i18n/messages/es.settings.ts
+4 -1
View File
@@ -1839,7 +1839,10 @@ export const settingsDict = {
"settings.voice.page.provider.server": "Servidor",
"settings.voice.page.provider.local": "Local",
"settings.voice.page.tooltip.sttLocal": "Transcripción local en el servidor de OpenChamber. Los modelos se descargan automáticamente; no se necesita clave de API.",
"settings.voice.page.tooltip.localTts": "Síntesis local en el servidor de OpenChamber (Kokoro, inglés). El modelo se descarga automáticamente; no se necesita clave de API.",
"settings.voice.page.tooltip.localTts": "Síntesis local en el servidor de OpenChamber (Kokoro para inglés; los modelos de otros idiomas se descargan en el primer uso). No requiere clave de API.",
"settings.voice.page.field.followTextLanguage": "Ajustar la voz al idioma del texto",
"settings.voice.page.field.followTextLanguageAria": "Ajustar la voz al idioma del texto",
"settings.voice.page.field.followTextLanguageInfo": "Si una respuesta está en otro idioma, se usa una voz para ese idioma: una voz de macOS adecuada o un modelo local que se descarga en el primer uso.",
"settings.voice.page.stt.model.parakeetV2": "Parakeet v2 (inglés)",
"settings.voice.page.stt.model.parakeetV3": "Parakeet v3 (25 idiomas europeos)",
"settings.voice.page.stt.model.whisperBase": "Whisper base (multilingüe)",