This commit is contained in:
Timothy Jaeryang Baek
2026-04-19 15:49:42 +09:00
parent a4d62253df
commit 5087492e25
2 changed files with 75 additions and 66 deletions
@@ -185,6 +185,7 @@
let speakingIdx: number | undefined;
let loadingSpeech = false;
let speakAbort: AbortController | null = null;
let showRateComment = false;
@@ -202,39 +203,39 @@
};
const stopAudio = () => {
speakAbort?.abort();
speakAbort = null;
try {
speechSynthesis.cancel();
$audioQueue?.stop();
} catch {}
if (speaking) {
speaking = false;
speakingIdx = undefined;
}
speaking = false;
speakingIdx = undefined;
loadingSpeech = false;
};
// Resolve voice: model-specific > user settings > config default
const getVoiceId = () =>
model?.info?.meta?.tts?.voice ??
($settings?.audio?.tts?.defaultVoice === $config.audio.tts.voice
? $settings?.audio?.tts?.voice ?? $config?.audio?.tts?.voice
: $config?.audio?.tts?.voice);
const speak = async () => {
if (!(message?.content ?? '').trim().length) {
toast.info($i18n.t('No content to speak'));
return;
}
stopAudio();
speakAbort = new AbortController();
const { signal } = speakAbort;
speaking = true;
const content = removeAllDetails(message.content);
// Get voice: model-specific > user settings > config default
const getVoiceId = () => {
// Check for model-specific TTS voice first
if (model?.info?.meta?.tts?.voice) {
return model.info.meta.tts.voice;
}
// Fall back to user settings or config default
if ($settings?.audio?.tts?.defaultVoice === $config.audio.tts.voice) {
return $settings?.audio?.tts?.voice ?? $config?.audio?.tts?.voice;
}
return $config?.audio?.tts?.voice;
};
if ($config.audio.tts.engine === '') {
let voices = [];
const getVoicesLoop = setInterval(() => {
@@ -242,16 +243,10 @@
if (voices.length > 0) {
clearInterval(getVoicesLoop);
const voiceId = getVoiceId();
const voice = voices?.filter((v) => v.voiceURI === voiceId)?.at(0) ?? undefined;
console.log(voice);
const voice = voices.find((v) => v.voiceURI === getVoiceId());
const speech = new SpeechSynthesisUtterance(content);
speech.rate = $settings.audio?.tts?.playbackRate ?? 1;
console.log(speech);
speech.onend = () => {
speaking = false;
if ($settings.conversationMode) {
@@ -281,9 +276,7 @@
);
if (!messageContentParts.length) {
console.log('No content to speak');
toast.info($i18n.t('No content to speak'));
speaking = false;
loadingSpeech = false;
return;
@@ -303,41 +296,43 @@
await $TTSWorker.init();
}
for (const [idx, sentence] of messageContentParts.entries()) {
for (const [, sentence] of messageContentParts.entries()) {
if (signal.aborted) return;
const url = await $TTSWorker
.generate({
text: sentence,
voice: voiceId
})
.generate({ text: sentence, voice: voiceId })
.catch((error) => {
console.error(error);
toast.error(`${error}`);
speaking = false;
loadingSpeech = false;
});
if (signal.aborted) return;
if (url && speaking) {
$audioQueue.enqueue(url);
loadingSpeech = false;
}
}
} else {
for (const [idx, sentence] of messageContentParts.entries()) {
for (const [, sentence] of messageContentParts.entries()) {
if (signal.aborted) return;
const res = await synthesizeOpenAISpeech(localStorage.token, voiceId, sentence).catch(
(error) => {
console.error(error);
toast.error(`${error}`);
speaking = false;
loadingSpeech = false;
}
);
if (signal.aborted) return;
if (res && speaking) {
const blob = await res.blob();
const url = URL.createObjectURL(blob);
$audioQueue.enqueue(url);
loadingSpeech = false;
}