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/web/server/lib/dictation/service.js
+27 -4
View File
@@ -1,3 +1,4 @@
import { detectTextLanguage } from '../tts/language-detect.js';
/**
* Dictation service: resolves STT providers, tracks local model download
* state, and exposes a readiness snapshot for the status route.
@@ -16,6 +17,8 @@ import { OpenAICompatibleTranscriptionSession } from './openai-compatible-sessio
import {
DEFAULT_LOCAL_STT_MODEL,
DEFAULT_LOCAL_TTS_MODEL,
getLocalTtsDefaultSpeaker,
resolveLocalTtsModelForLanguage,
LOCAL_STT_MODEL_CATALOG,
LOCAL_STT_MODEL_IDS,
LOCAL_TTS_MODEL_CATALOG,
@@ -220,10 +223,30 @@ export function createDictationService({ modelsDir }) {
/**
* Synthesize speech with the local TTS model. Returns WAV bytes, or a
* readiness error while the model is missing/downloading.
* @param {{ text: string, model?: string, speakerId?: number, speed?: number }} options
*
* With `language: 'auto'` the text's language decides the model: the
* caller's model when it speaks that language, otherwise the catalog
* model for it (downloaded on first use, reported as in-progress until it
* lands). The caller's speaker id is kept only on the caller's model; a
* substitute model starts from its own default speaker for the language.
* A language no catalog model covers keeps the caller's model, so text is
* never silently dropped.
* `languageSample` is the whole message the chunk belongs to (or a prefix
* of it): the language is judged on that, never on a short chunk alone.
* @param {{ text: string, model?: string, speakerId?: number, speed?: number, language?: string, languageSample?: string }} options
*/
const synthesizeSpeech = async ({ text, model, speakerId, speed }) => {
const modelId = isLocalTtsModelId(model) ? model : DEFAULT_LOCAL_TTS_MODEL;
const synthesizeSpeech = async ({ text, model, speakerId, speed, language, languageSample }) => {
const requestedModelId = isLocalTtsModelId(model) ? model : DEFAULT_LOCAL_TTS_MODEL;
let modelId = requestedModelId;
let resolvedLanguage = null;
if (language === 'auto') {
resolvedLanguage = detectTextLanguage(languageSample || text).language;
const forLanguage = resolveLocalTtsModelForLanguage(resolvedLanguage, requestedModelId);
if (forLanguage && forLanguage !== requestedModelId) {
modelId = forLanguage;
speakerId = getLocalTtsDefaultSpeaker(modelId, resolvedLanguage);
}
}
const installed = await isLocalSttModelInstalled(modelsDir, modelId);
if (!installed) {
const state = downloadStates.get(modelId);
@@ -251,7 +274,7 @@ export function createDictationService({ modelsDir }) {
speakerId,
speed,
});
return { audio: result.audio, format: result.format };
return { audio: result.audio, format: result.format, modelId, language: resolvedLanguage };
};
/**